Learning Track: Advanced Algorithmic Trading Strategies

59 Hours

A perfect bundle of courses for traders who want to enhance trading by using advanced trading strategies. Learn strategies such as momentum, mean-reversion, index arbitrage, long-short, and triplets trading strategies. Learn to generate time series, and cross-sectional alphas, and alpha optimisation. Learn all about medium-frequency trading (MFT) and order flow analysis. Explore machine learning techniques for momentum strategies. Gain practical Python skills and deployable trading models.

Level

BEGINNER to ADVANCED

Authors

Dr. Ernest P. Chan

QuantInsti®

Dr. Thomas Starke

Price Lifetime Access Limited Time Offer

₹55880 /-₹69850/-

Original Price: ₹279394

75% OFF

+ Additional 20% OFF

Live Trading
Learning Track
Prerequisites
Syllabus
About author
Testimonials
Faqs

Learn Advanced Trading Strategies

Learn about mean reversion trading strategies taught by Dr Ernest Chan, who employed these techniques in his own hedge fund.

Create and backtest the time series and cross-sectional momentum strategies on stocks, stock indices, fixed income, commodities, and futures markets.

Apply machine learning techniques to enhance traditional momentum trading strategies.

Learn the ins and outs of medium-frequency trading(MFT), order flow analysis, different types of orders taught by Dr Ernest Chan.

Find micro-alphas, optimise the parameters without overfitting and combine the alphas taught by seasoned Quant Dr Thomas Starke.

Backtest, add stop-loss and profit-take by using a vectorized approach.

One-click integration of quantitative models into a live trading platform to analyse strategies in a live trading environment.

Skills Covered

Strategy Paradigms

Statistical & Index Arbitrage
Momentum Trading
K-Nearest Neighbours
Timing Alphas
Order flow trading using tick

Math & Core Concepts

ADF and Johansen Test
System Parameter Permutation
ML Classification & Clustering
Spoofing and Front-running
Lee-Ready Algorithm and BVC Rule

Python Libraries

Adfuller, Statstools, Johansen
NumPy, Pandas, Matplotlib
Sklearn
Asyncio
XGboost, SciPy

learning track 8

Advanced Algorithmic Trading Strategies

BEGINNER

News Sentiment Trading Strategies₹8550
₹8550

INTERMEDIATE

Mean Reversion Strategies In Python₹13750
₹13750
Momentum Trading Strategies₹8675
₹8675

ADVANCED

Trading Alphas: Mining, Optimisation, and System Design₹14300
₹14300
Trading in Milliseconds: MFT Strategies & Setup₹13825
₹13825
Advanced Momentum Trading: Machine Learning Strategies₹10750
₹10750

BEGINNER

News Sentiment Trading Strategies

INTERMEDIATE

ADVANCED

Full Learning Track

These courses are specially curated to help you with end-to-end learning of the subject.

Need help? Write to us at quantra@quantinsti.com or call us at +91 8450963428.

Ready to Master Algorithmic Trading?

Elevate your trading skills with our comprehensive 'All Courses Bundle.' With 50 expertly designed courses organized into 8 specialized learning tracks, you'll gain a complete A-to-Z understanding of algorithmic trading strategies and techniques.

Course Features

Community
Faculty Support on Community
Interactive Coding Exercises
Interactive Coding Practice
Capstone Project
Capstone Project using Real Market Data
Trade & Learn Together
Trade and Learn Together
Get Certified
Get Certified

Prerequisites

You should understand the basic terminology around financial markets such as sell, buy, margin, entry, exit positions, etc. Ability to work with numpy and pandas dataframe in Python. Knowledge of machine learning concepts such as train-test split, features and forecasting, and clustering techniques. You may also want to familiarise yourself with basics of momentum trading.

Advanced Trading Strategies Course

News Sentiment Trading Strategies

Introduction

An approach to trading that focuses on the retrieval of news data and analysing the sentiment to make data-driven decisions is news-based trading. This section serves as a preview of the course and introduces the course contents. The interactive methods used in this course will assist you in not only understanding the concepts but also answering all questions regarding sentiment analysis. This section explains the course structure as well as the various teaching tools used in the course, such as videos, quizzes, coding exercises, and the capstone project.

Introduction to the Course

3m 54s

Course Structure Flow Diagram

2m

Course FAQs

2m

Quantra Features and Guidance

4m 9s
About News-Based Trading

In this section, you will understand why you should trade the news and how it can help you in improving your ability to make well-informed decisions and capitalise on market opportunities in a dynamic and ever-changing landscape. Having access to reliable and timely news sources is essential for traders to interpret and respond to market-moving events effectively. Therefore, in this section you will also learn about some of the sources of news.

Why Trade the News?

2m

Trading the News

5m

Benefits of Trading the News

5m

Trading Volatility

5m

Trading the News and Technical Analysis

5m

Price Movements

5m

News-Based Trading and Volatility

5m

Sources of News

5m 08s

Company News

5m

Official Announcements

5m

Expert Opinions and Research Reports

5m

Importance of Research Reports

5m

Unstructured News

5m

General Public Influence

5m

Role of Media Houses

5m

Additional Reading on News Based Trading

2m

FAQs on News Based Trading

2m
Types of News Releases

News comes in various forms so in this section we’ve broadly classified news into two categories - planned and unexpected news. After completing this section, you will learn how news can be categorised and get an idea of the impact that news can have on the market.

Planned News

3m 45s

Categorising News Releases

5m

Corporate News Releases

5m

Identifying Planned News

5m

FOMC News Release

5m

Economic News Releases

5m

Impact of Planned News Releases

5m

Unexpected News

3m 31s

Planned and Unexpected News

5m

Identifying Unexpected News

5m

Trading the Unexpected News

5m

Unexpected Events

5m

News Based Trading Practices

5m

Additional Reading on Impact of News Based Trading

2m
Buy the Rumour

In this section, you will examine the reason why traders buy a stock on a rumour which has not been officially confirmed.

Buy the Rumour

1m 08s

Role of Information in Trading

5m

Rumours on Product

5m

Verification of Rumour

5m

View Regarding Product Launch

5m
Sell at the Event

In this section, you will discuss a contrarian strategy where you have bought the stock on the basis of rumours but sell it on the day of the event irrespective of the event’s outcome.

Sell at the Event

2m 4s

Reasoning for Stock Buy

5m

Reaction to News on Product Launch

5m

Selling Stock

5m

Outcome of Buy the Rumour Sell the Event

5m

Observation of Buy the Rumour and Sell the Event

5m

Risk of Buy the Rumour and Sell the Event

5m

Consistency of Buy the Rumour Sell the Event

5m
Backtest the Buy Rumour and Sell Event Strategy

You have seen the logic of the trading strategy where you will buy the stock on the rumour and sell at the event. Now, it is time to backtest and analyse this strategy

Buy the Rumour Sell the Event

5m

Read the Data

5m

Find the Date 20 Days Prior to Event

5m

List the Dates From Event and 20 Days Prior to Event Date

5m

Generate Trading Signal for Buy Rumour Sell the Event

5m

Calculate Daily Returns

5m

Calculate Portfolio Strategy Daily Returns

5m

Calculate Cumulative Returns

5m

Calculation of CAGR

5m

Calculate the Sharpe Ratio

5m

Calculate Maximum Drawdown

5m
Limitations of Buy the Rumour Sell the Event

The buy the rumour and sell at the event strategy is not without its flaws. In this section, you will analyse the strategy and its limitations. And further, explain how it can be improved.

Limitations of Buy the Rumour and Sell at the Event

2m

Trading Strategy Application Boundary

5m

Logic of Buy the Rumour Sell the Event

5m

Influence of Other Factors on Strategy

5m

Inference on Buy the Rumour Sell the Event Strategy

5m

FAQs

2m
Retrieving and Storing Textual Data

Step 1 of creating a news sentiment analysis strategy is to retrieve news-related data. In this section, you will retrieve news data and learn how to store it in a format which can be easily retrieved and analysed.

Retrieving and Storing Textual Data

3m 2s

Web Scraping

5m

Website Crash

5m

Prevent Server Crash

5m

APIs

5m

Load Balancing

5m

Benefit of APIs

5m

Store Sentiment Data

5m

Tweepy API

2m

Alpaca API

2m

Working With Pickle File

5m

Fetching News Data

5m
Qualitative Analysis

The quality of data that we use also determines the effectiveness of our strategy. Therefore, in this section, you will delve into various methods to enhance the data quality. We will focus on refining and filtering the data through Python to elevate its overall quality and reliability.

Qualitative Analysis

3m 59s

Goal of Qualitative Analysis

5m

Contentless Articles

5m

Determining Relevance

5m

Define Novelty

5m

Importance of Novelty

5m

Duplicate News Articles

5m

Qualitative Analysis

5m

Remove HTML Tags

5m

Drop Duplicate Articles

5m

Ensuring Novelty

5m

Sort the News Data

5m

Transform the Data

5m

Similarity Score

5m

Test on Trading the News and News Data

16m

FAQs on Qualitative Analysis

2m
Using News to Your Advantage

In this section we will discuss how we can use the news data to our advantage.

How to Use News to Your Advantage?

2m 36s

Calculating Sentiment Scores

5m

Challenge in ML Approach

5m

VADER

5m

Lexical-Based Approach

5m

Advantage of VADER

5m

Positive Sentiment Score

5m

Lexical-Based Sentiment Analysis

5m

Sentiment Dictionary

5m

Labelled Data

5m

Full Form of VADER

5m
Sentiment Score Using VADER

In this section, you will learn about how VADER calculates sentiment score for a text. In addition to this, this section also covers the concepts such as how VADER accounts for sentiment intensity and the limitations of VADER.

How Vader Calculates the Sentiment Score

6m 46s

Why is VADER preferred?

5m

Purpose of VADER's Compound Score

5m

VADER's Lexicon Dictionary

5m

Calculation of Compound Score

5m

The Range of Compound Score

5m

Range of Sentiment Scores

5m

How VADER Accounts for Sentiment Intensity

1m 43s

Sentiment Intensity - Capitalisation

5m

VADER’s Rule for Sentiment Intensity

5m

Impact of Sentiment Intensity

5m

Effect of Contrastive Conjunctions

5m

Effect of Punctuation Rule of VADER

5m

Additional Reading for Sentiment Score Using VADER

2m

FAQs on Sentiment Score Using VADER

2m

Section Recap

2m
Limitations of VADER

This section covers the limitations of VADER for Sentiment Analysis of news headlines.

Limitations of VADER for Sentiment Analysis

1m 13s

Limitations of VADER - I

5m

VADER to Analyse Sarcasm

5m

Limitations of VADER - II

5m

Interpretation of Financial Terms by VADER - I

5m

Interpretation of Financial Terms by VADER - II

5m

Add New Words to VADER

5m
Calculate Sentiment Score in Python

This section covers the implementation of VADER in Python for calculating the sentiment score of words and news headlines. This section also covers the VADER methods to access its lexicon and update it with financial words.

VADER Score Calculations

5m

Create The Analyzer Object

5m

Generate Sentiment Scores of a News Headline

5m

Calculate Compound Score of News Headline

5m

Sentiment Intensity of Headlines

5m

Add New Words in VADER Dictionary

5m

Access the Vader Lexicon

5m

Python Code to Update VADER Lexicon

5m

Update the VADER Lexicon

5m

Sentiment Score of a Word

5m

Calculate Sentiment Scores of News Headlines

5m

Sentiment Score of a News Headlines

5m

Additional Reading for Calculate Sentiment Score In Python

2m

FAQs on Calculate Sentiment Score In Python

2m

Section Recap

2m

A Guide to Vader Library and Its Methods

2m

Test on Sentiment Analysis With VADER

14m
Challenges in Calculating Sentiment of News

Calculation of Sentiments in news articles is not as straight-forward as we thought. In this section, you will lean about the challenges in effectively calculating news sentiments and how to overcome them.

Challenges in Calculating Sentiments of News

2m

Limitations of Using First or Last Few Sente

2m

Limitations of Selectively Checking Sentences

2m

Calculating Sentiment of News Articles

10m

Method to Split Article into Sentences

2m

Last Five Sentences

2m

Appropriate Keyword

2m
Sentiment Analysis Using LLMs

Large Language Models (LLMs) harness the power of artificial intelligence to make our life easier. LLMs are inherently using sentiment analysis for this purpose. Thus, you will see how you can perform sentiment analysis using LLM.

Sentiment Analysis Using LLMs

2m 5s

Usage of LLMs

5m

Steps in Sentiment Analysis

5m

LLM-Based Sentiment Analysis

5m

Passing the Data

5m

Benefits of LLMs

5m

LLMs and Its Use Cases

2m

Limitations of LLMs in Sentiment Analysis

2m

Sentiment Analysis Using Gemini

5m
Calculation of Daily News Sentiment Score

In this section, you will calculate the news sentiment score for each day using VADER. This will help us in creating a strategy around sentiment analysis

Calculate Daily News Sentiment

5m

Extract the Date From a Column

5m

Calculate Compound Sentiment Score for Headline

5m

Filter Out News with Non-Zero Sentiment Scores

5m

Calculate Normalised Sentiment Score for the Day

5m

Sum the Normalised Sentiment Scores for Each Date

5m
Buy the Rumour Sell the Event With Sentiment Analysis

The buy the rumour and sell the event strategy did not include any news-related analysis. In this section, you will seek to improve your trading strategy by using sentiment scores which were calculated in the previous sections.

Buy the Rumour Sell the Event Using Sentiment Scores

2m

Purpose of Incorporation of Sentiment Scores

5m

Drawback of Not Considering News Events

5m

Significance of Setting Sentiment Score Based Threshold

5m

Rolling Sentiment Score

5m

Calculation of Average Sentiment Score

5m

Decision when Average Sentiment Score is Positive

5m

Action if Day is Prior to Event

5m

Time of Exit

5m

Incorporating Sentiment in Buy the Rumour Sell the Event

2m

Incorporating Sentiment in Buy the Rumour Sell the Event

5m

Calculate Rolling 20-Day Mean of Sentiment Scores

5m

Join Sentiment Score and Price in One Dataframe

5m

Generate Trading Signal for Sentiment Score and Event Day Condition

5m
Analysis of Buy Rumour Sell Event Using Sentiment Scores Strategy

You have backtested the Buy the Rumour Sell at the Event Using Sentiment Scores Strategy in the previous section. Now, you will check if there is a way to improve the strategy performance

Analysis of the Buy the Rumour Sell at the Event Using Sentiment Scores Strategy

2m

Limitation of Buy the Rumour Sell the Event Strategy

5m

Enhancement of Buy Rumour Sell Event With Sentiment Scores Strategy

5m

Action if Sentiment Score is Negative

5m

Elimination of Condition in Enhanced Strategy

5m
Sentiment Analysis Strategy

The sentiment analysis strategy seeks to use the average sentiment score to generate trading signals. You will implement this strategy and analyse the strategy performance.

Flow Diagram for Sentiment Analysis Strategy

2m

Sentiment Analysis Strategy

5m

Entry Rule for Sentiment Analysis Strategy

5m

Threshold of Sentiment Score to Generate Trading Signals

5m

Time Frame of Average Sentiment Score

5m

Generate Sentiment Based Trading Signal

5m
Improving the Sentiment Analysis Strategy

The sentiment analysis based strategy was backtested and analysed. But now, you will see how you can improve the strategy further by using technical indicators.

Analysing Sentiment Analysis Strategy Performance

2m

Performance of Sentiment Analysis Strategy

5m

Improvement in Quality of Trading Signal

5m

Combined Strategy Improvement

5m

Flow Diagram for Improving Sentiment Analysis Strategy

2m

Improving Sentiment Analysis Strategy Using Technical Indicators

5m

Calculate the 14-Day Period RSI Indicator

5m

Generate the Entry Signal for RSI Indicator

5m

Generate Exit Signal for RSI Indicator

5m

Enhancing Sentiment Analysis Strategies With Technical Indicators

5m

Expanding Information Scope in Trading With Technical Indicators

5m

Test on Sentiment Analysis Based Strategies

10m

FAQs

2m

Part Summary

2m
Pitfalls of Trading the News

While news-based trading presents valuable prospects for leveraging information to our advantage, it is not free of challenges. In this section, you will explore the key challenges associated with news-based trading and you will also learn some ways to counter these challenges.

Common Pitfalls of News Based Trading

4m 19s

Importance of Credibility

5m

Credible Sources

5m

Sentiment Forecasts

5m

Latency in Getting Data

5m

Confirming Signals

5m
Capstone Project

In this section, you will use the learnings from the course to use VADER to design a trading strategy based on daily sentiment score of a stock. You will also check the performance of this trading strategy.

Getting Started

2m

FAQs

2m

Problem Statement

2m

Capstone Project Solution

5m
Live Trading on IBridgePy

In this section, you would go through the different processes and API methods to build your own trading strategy for the live markets, and take it live as well.

Uninterrupted Learning Journey with Quantra

2m

Section Overview

2m 2s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Code Structure

2m 15s

API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

IBridgePy Course Link

10m

Additional Reading

10m

Frequently Asked Questions

10m
Paper and Live Trading

To make sure that you can use your learning from the course in the live markets, a live trading template has been created which can be used to paper trade and analyse its performance. This template can be used as a starting point to create your very own unique trading strategy.

Template Documentation

10m

Template Code File

2m
Summary

In this section, we will summarise all the learnings of this course.

Course Summary

2m

Course Summary and Next Steps

2m

Python Codes and Data

2m

Mean Reversion Strategies In Python

Introduction to the Course

This section gives an overview of the mean reversion strategy through examples. You will go through the course structure and understand how the course is structured in videos, quizzes, strategy codes and interactive coding exercises. This will make sure that not only do you understand the mechanics of mean reversion but also implement trading strategies in live markets.

Introduction by Dr. Ernest Chan

2m 19s

Introduction to Mean Reversion Strategy

3m 48s

Course Structure Flow Diagram

10m

Quantra Features and Guidance

3m 48s

Types of Statistical Arbitrage Strategies

5m 7s

Frequently Asked Questions

10m
Stationarity of Time Series

Stationary is one of the essential concepts upon which pairs trading and other cointegrated trading is built. This section discusses the concept of stationary through real price data and how it is different from the random walk.

What is Stationarity?

2m 15s

Mean Reversion Trading Approach

2m

Temporary Mean Reversion

2m

Stationarity

2m

Statistical Test for Stationarity

2m
Why Use the ADF Test

In this section, you will understand why you should use the ADF (Augmented Dickey-Fuller) Test and understand the significance of the lambda parameter in the context of the test. Additionally, you will also develop the intuition behind the calculation of lambda within a price series, providing insights into its role in identifying stationarity.

Why Use the ADF Test?

2m

Issue With Visual Approach

5m

Augmented Dickey-Fuller Test

5m

Advantage of Using ADF Test

5m

Terms of ADF Test Equation

2m

Role of Lambda In ADF Test

2m

Null Hypothesis in ADF Test

5m

Interpretation of Negative Value in Lambda

5m

Interpretation of Non-Negative Value of Lambda

5m

Alternative Hypothesis in ADF Test

5m

Use of Lambda in ADF Test

5m

Pre Reading Materials

10m

Calculation of Lambda in Price Series

2m

Implication of Mean Reversion

5m

Role of Covariance

5m

Short Form of ADF Test Equation

5m
Intuition of ADF Test Equation

In this section, you will explore the intuition behind the ADF test equation, focusing on the role of lambda and standard error in determining stationarity, and learn how to interpret the results using critical values.

Intuition of ADF Test Equation

2m

First Step in Stationary Series Determination

5m

Comparison to Critical Values Table

5m

Interpretation of Critical Values Table

5m

Observation of Value Less Than Critical Values Table

5m
Augmented Dickey-Fuller Test

This section starts with the revision of the mathematics behind the Augmented Dickey-Fuller (ADF) test, which is used to check whether the price series is stationary or not. You will also learn to check the stationarity of currency pairs in Python.

Math Behind ADF Test (Optional)

5m

Critical Value and Test Statistics

2m

How to Use Jupyter Notebook?

2m 5s

ADF Test on CADUSD Pair

10m

Calculate Test Statistics

5m

Import Library and Read CSV

5m

Limitations of the ADF Test

2m

Low Power in Small Samples

5m

Lag Length Sensitivity

5m

Structural Breaks in Time Series

5m

Non-Linear Trends and the ADF Test

5m

Detecting Near-Unit Root Processes

5m

Model Dependency

5m

FAQs on ADF Test

2m

Additional Reading

10m
Mean Reversion Strategy

In this section, you will learn to create and backtest a trading strategy based on the concept of mean reversion. You will learn to use the Bollinger Bands to create a mean reversion strategy on a currency pair.

Mean Reversion Strategy

1m 47s

Upper Band

2m

Trading Based on Mean Reversion

2m

Mean Reversion Strategy on AUDCAD

10m

Calculate Moving Average and Standard Deviation

5m

Upper and Lower Band

5m

Long Entry and Exit

5m

Short Entry and Exit

3m

Long and Short Positions

5m

Forward Fill Missing Positions

5m

Consolidate the Positions

5m

Compute PnL

5m

Recap

1m 47s

Frequently Asked Questions

10m

Test on Stationarity, ADF and Mean Reversion

16m
Live Trading on Blueshift

This section will walk you through the steps involved in taking your trading strategy live. You will learn about backtesting and live trading platform, Blueshift. You will learn about code structure, various functions used to create a strategy and finally, paper or live trade on Blueshift.

Uninterrupted Learning Journey with Quantra

2m

Section Overview

2m 19s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Blueshift Code Structure

2m 57s

Important API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

Backtest and Live Trade on Blueshift

4m 5s

Additional Reading

10m

Blueshift Data FAQs

10m
Live Trading Template

In this section, a live trading strategy template will be provided to you. The template strategy will be on the mean reversion strategy covered in the previous section. You can tweak the code by changing different currency pairs, date range to backtest and finally analyse the strategy performance in more detail.

Paper/Live Trading FX Mean Reversion Strategy

10m

FAQs for Live Trading on Blueshift

10m
Cointegration

If a linear combination of two or more price series is stationary, then the individual price series are said to be cointegrated with each other. This section introduces cointegration between two-time series and covers a test for detecting cointegration of a portfolio of instruments called the cointegrated augmented Dickey-Fuller (CADF) test.

What is Cointegration?

2m 58s

Cointegration

2m

Correlation

2m

What is Hedge Ratio?

5m 48s

Portfolio Formation Using Hedge Ratio

2m

Hedge Ratio Code

2m 26s

Import Library

5m

Calculate Hedge Ratio

5m

What is CADF Test?

4m 2s

Check Cointegration using CADF Test

5m

Order Dependence of CADF

10m
Pairs Trading

Most financial instruments are not stationary, and creating a mean reversion strategy is not possible on such a price series. To overcome this issue, you need two price series which are cointegrated with each other. In this section, you will learn to create a pairs trading strategy using the Bollinger Bands. You will also learn to backtest the same in Python.

Mean Reversion Strategy on Pairs

2m 49s

Mean Reversion Strategy on GLD-GDX

10m

Take Long Entry and Exit

5m

Compute Strategy PnL

5m

Paper/Live Trading Pair Trading Strategy

10m

Additional Reading

10m

Recap

2m 14s

Mean Reversion Strategy

15m 35s
Triplets

This section discusses failure of the mean reversion strategy of the GLD-GDX pair. Based on the possible reason we will arrive at the conclusion of choosing a triplet to improve the mean reversion strategy. The working of Johansen test will be explained to arrive at the hedge ratios for the new mean reversion strategy for triplets. This section also covers the concept of half-life of mean reversion along with Ornstein-Uhlenbeck formula for computing the half-life of mean reversion.

Cointegration Breakdown in the GLD-GDX Pair

5m 5s

Reason of Breakdown of Cointegration

2m

Significance of Cointegration

2m

Surviving Breakdown of Cointegration

5m 17s

How to Survive Breakdown of Cointegration?

2m

Breakdown Remedies

2m

Optimization Problems

2m

Eigenvalues and Eigenvectors

2m

What is Johansen Test?

6m 27s

CADF Shortcomings

2m

Linear Combination

2m

GLD-GDX Cointegration Test

4m

Mean Reversion on Triplets

3m 49s

Mean Reversion on Triplets Code

10m

GLD-GDX-USO Cointegration Test

4m

Cointegration Test

2m

Taking Positions

2m

Recap

1m 11s

Frequently Asked Questions

10m
Half Life

This section explains how long would it it take for the time series to revert back to the mean. And the importance of half-life to select the right instruments to trade in.

Half Life of Mean Reverting Time Series

4m 12s

Half Life

2m

Half Life Formula

2m

Half-Life Using Johansen Test

10m

Compute Half-Life of GLD-GDX

5m

Frequently Asked Questions

10m
Risk Management

This section explains the importance and two common usages of stop loss in mean reverting strategies. Further, you will learn to backtest mean-reverting strategy with and without stop and compare the performance of the strategy.

Stop-Loss

5m

Mean Reversion Strategy With Stop Loss

10m
Best Markets to Pair Trade

This section explains the pros and cons of mean reversion strategies in different markets such as exchange traded funds (ETFs), stocks, currencies, and futures. Further, in the section, will understand how economically related pairs do not co-integrate, cover the basic concept of crack spread and test for stationarity of crack spread.

Best Markets To Pair Trade

5m 18s

Mean Reversion of ETF Pairs

2m

Mean Reversion of Stock Pairs

2m

Mean Reversion of Currencies and Futures

2m

Cointegration Test of CL and BZ

10m

Cointegration Test of Crack Spread

10m

Identify Cointegrated Stock Pairs

10m
Index Arbitrage

This section explains Index Arbitrage Strategy which is an extension of pairs and triplets, how to construct a basket of instruments and see the difficulties of trading an Index Arbitrage strategy.

Index Arbitrage Strategy

3m 49s

Working of Index Arbitrage Strategy

2m

Custom Basket

2m

Index Arbitrage Strategy Code

10m

Difficulties in Index Arbitrage

2m
Long Short Portfolio

This section explains the concept of long-short portfolio strategy, how it is different from other mean reversion strategies. Further, will construct a long-short portfolio of stocks in the S&P 500, understand the importance of universe selection of stocks on strategy and learn to refine a strategy.

Long-Short portfolio Strategy

3m 39s

Long-Short Portfolio

2m

Strategy Formula

2m

Long-Short Portfolio Strategy Code

10m

Calculate Stock Returns

5m

Calculate Market Returns

5m

Calculate Dollar Allocation for Each Stock

5m

Calculate Sharpe Ratio

5m

Paper/Live Trading Long-Short Strategy

10m

Analysis of Strategy Performance

5m

Test on Trading Based on Mean Reversion

18m
Run Codes Locally on Your Machine

Learn to install the Python environment in your local machine.

Python Installation Overview

2m 18s

Flow Diagram

10m

Install Anaconda on Windows

10m

Install Anaconda on Mac

10m

Know your Current Environment

2m

Troubleshooting Anaconda Installation Problems

10m

Creating a Python Environment

10m

Changing Environments

2m

Quantra Environment

2m

Troubleshooting Tips For Setting Up Environment

10m

How to Run Files in Downloadable Section?

10m

Troubleshooting For Running Files in Downloadable Section

10m
Automated Trading Using IBridgePy

A live trading strategy template will be provided to you. You can tweak the template to deploy your strategies on Interactive Brokers using IBridgePy API.

Additional Reading

10m

Sample Strategy to Run on Interactive Brokers

2m
Summary

Course Summary

3m 52s

Python Codes and Data

2m

Momentum Trading Strategies

Introduction to the Course

Learn the application and effectiveness of momentum trading strategies. You will be guided through the course structure and the various concepts covered in the course. Explore various features that are available to you on Quantra.

Introduction to Momentum Trading

3m 59s

Course Structure

3m 22s

Course Structure Flow Diagram

2m

Quantra Features and Guidance

3m 48s
What is Momentum?

Momentum is the tendency of a financial security to continue its price movement in the given direction. After completing this section, you will also be able to analyse four myths which prevail in the world of momentum.

Introduction to Momentum

2m 42s

Definition of Momentum

2m

Display of Momentum

2m

Historical Record of Momentum

2m

Myths of Momentum

3m 6s

Secret of Momentum

2m

Gains Through Momentum Trading

2m

Truth About Momentum Myths

2m

What is Momentum Additional Reading

2m
Why Does Momentum Exist?

In this section, you will learn the reasons for the existence of momentum, namely, herding effect, slow diffusion of news, the persistence of roll returns in futures, forced sales and purchases by fund houses. This will give you an insight into where to find momentum and what causes it.

Why Momentum Exists - I

1m 49s

Herding Effect Definition

2m

Herding Effect Towards Amazon

2m

Why Momentum Exists - II

2m 36s

Reason for PEAD Effect

2m

Momentum in Futures

2m

Why Momentum Exists - III

3m 3s

Reasons for Momentum

2m

Effect of Client Redemptions

2m

Performance of Leveraged ETFs

2m

Index Tracker Fund Performance

2m

References and Additional Reading

2m

Test on Fundamentals of Momentum

12m
Introduction to Python

This section will help you update your knowledge of Python with simple exercises on implementing functions, and manipulating dataframes using Numpy and Pandas libraries. The Quantra environment ensures that you don’t have to install anything for the Jupyter notebooks to function.

Uninterrupted Learning Journey with Quantra

2m

Need for Python

3m 4s

Preference for Python

2m

Functionality of Python

2m

How to Use Jupyter Notebook?

1m 54s

Print Statement

5m

My First Jupyter Notebook

10m

Getting Started with Interactive Exercises

5m

Operations and Functions in Python

10m

Divide Two Numbers

5m

Pandas Dataframe

2m 22s

Function Call

5m

DataFrame Axis Label

2m

DataFrame and Basic Functionality

10m

DataFrame Syntax

2m

Dropping/Deleting Columns

2m

Create Pandas DataFrame

5m

DataFrame Indexing

2m

Print Columns

2m

Access Elements of a DataFrame

5m

Add New Column to a DataFrame

5m

Set Column as Index

5m

Add Values of a Column

5m

Additional Reading

10m
Financial Market Data and Visualisation

An important component of a successful strategy is the data set used. In this section, you will learn how to import the correct data from various web resources, so that you can work on your own unique strategy.

Importing Data

1m 39s

Correct Syntax for Importing Stock Data

2m

Importing Time Series Data

10m

Data Visualisation

10m

Plot Line Graph

5m

Plot Bar Graph

5m

Additional Reading

10m

Frequently Asked Questions

10m
Technical Indicators

Technical indicators are used to predict the future prices of assets by studying historical price series data. After completing this section, you will be able to differentiate between technical and fundamental analysis, and describe the crossover and breakout indicators. You will also be able to explain the idea of building a technical indicator based strategy on a custom portfolio rather than on individual stocks or indices.

Role of Technical Indicators

2m 37s

Use of Technical Analysis

2m

Momentum Technical Indicators

2m

Application of Technical Indicators

2m

Technical Vs Fundamental Analysis

2m

Additional Reading for Ta-Lib Installation

2m

Moving Averages

10m

Decision Based on Moving Average

2m

Moving Average in Stocks

2m

Breakout

10m

Calculation of Breakout Indicator

2m

Definition of Breakout Indicator

2m

Decision Based on Breakout

2m

Technical Indicator Additional Reading

2m
Technical Indicator Strategy

Learn to apply technical indicators on volatility decile portfolios. This helps to capture the power of volatility and the technical indicator. Also, learn to combine two technical indicators namely crossover and breakout, and analyse the equity curve, sharpe ratio and drawdown curve.

Technical Indicator Strategy

4m 7s

Volatility Decile Portfolio Definition

2m

Volatility Decile Portfolio Use

2m

Maximum Drawdown of Strategies

2m

Technical Indicators Strategy Logic

2m

Technical Indicators

10m

Read Data From CSV

5m

Calculate Daily Percentage Change

5m

Calculate Standard Deviation

5m

Annualise Standard Deviation

5m

Descending Order of Stocks

5m

Shortlist Volatility Decile

5m

Calculate Simple Moving Average

5m

Generate Trading Signal

5m

Moving Average Strategy Returns

5m

Sharpe Ratio

5m

Breakout and SMA

5m
Live Trading on Blueshift

This section will walk you through the steps involved in taking your trading strategy live. You will learn about backtesting and live trading platform, Blueshift. You will learn about code structure, various functions used to create a strategy and finally, paper or live trade on Blueshift.

Section Overview

2m 19s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Blueshift Code Structure

2m 57s

Important API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

Backtest and Live Trade on Blueshift

4m 5s

Additional Reading

10m

Blueshift Data FAQs

10m
Live Trading Template

Blueshift Live Trading Template

Paper/Live Trading Technical Indicator Strategy

10m

FAQs for Live Trading on Blueshift

5m
Types of Momentum

This section will help you explain time-series and cross-sectional momentum along with their examples. You will be able to apply this knowledge while creating trading strategies in the latter part of the course

Types of Momentum

2m

Identifying Winners

2m

Winner and Loser Ratio

2m

Additional Reading

10m
Time Series Momentum

The time series momentum focuses on a security’s own past return. Learn the concepts of lookback and holding period. Backtest the time series momentum strategy on stock indices, currencies, commodities, and treasuries. Analyse the performance of the strategy on different securities.

Time Series Momentum

2m 31s

Lookback and Holding Period

2m

Trading Decision Based on Returns

2m

Essential Points for Momentum Trading

2m

Reason for Underperformance of Strategy

2m

Time Series Momentum Strategy

10m

Convert Daily Frequency to Monthly Frequency

5m

Calculate Yearly Returns

5m

Generate Trading Signals

5m

Calculate Strategy Returns

5m

Plot Cumulative Curve

5m

Paper/Live Trading TSMOM on Single Asset

10m

Time Series Momentum on Multiple Asset

1m 59s

Does Momentum Strategy Work?

2m

Test for Trending Time Series

2m

TSMOM Strategy on Multiple Asset Classes

10m

Paper/Live Trading TSMOM on Multiple Assets

10m

Time Series Additional Reading

2m
Hurst Exponent

How to identify if the time series is trending? The answer is through Hurst exponent. You will learn the math behind Hurst exponent and its implementation in Python. Then, calculate the Hurst exponent of various securities across asset classes to find the trending time series.

Hurst Exponent

3m 32s

Why Hurst Exponent?

2m

What is the Hurst Exponent?

2m

Nature of Time Series

2m

Hurst Value

2m

Identify Time Series

2m

Hurst Exponent Calculation

5m

Hurst Exponent Explanation

10m

Steps in Hurst Exponent Calculation

2m

Calculate Rescaled Range

2m

Hurst Exponent on Multiple Asset Classes

10m

Calculate Hurst Exponent of Security

5m

Which Security is More Trending?

2m

High Hurst Exponent Securities

5m

Hurst Exponent Additional Reading

2m
Correlation Analysis

Correlation is used to find the relationship between time series. Learn to find the optimal lookback and holding periods for the time series momentum strategy using correlation analysis.

Correlation and P-Value

10m

Correlation and Covariance

2m

Statistical Significance Test

2m

Correlation Analysis

4m 9s

Role of P-Value

2m

Lookback and Holding Period for Crude Oil

2m

Optimal Lookback and Holding Period

10m

Calculate Correlation Coefficient

5m

Plot Correlation Coefficient Heatmap

5m

Filter Securities With Positive Correlation

5m

Additional Reading

10m

Course Summary - I

2m 26s

Test on Strategy Creation

12m
Cross Sectional Momentum

The cross sectional momentum works on the relative performance of the securities. You will learn to find the optimal lookback and holding periods and the criterion to select stocks for cross sectional momentum strategy. Finally, create a long-short and long only cross sectional momentum strategy on S&P 500 stocks and compare their performances.

Introduction to Cross Sectional Momentum

3m 37s

Types of Momentum

2m

Momentum in Returns

2m

Which Lookback and Holding Period?

2m

Cross Sectional Momentum Strategy

3m 43s

Factor to Filter Stocks?

2m

Steps for Cross Sectional Momentum Strategy

2m

Which Fund House?

2m

Impact of High Number of Stocks

2m

Strategy Flow Diagram

2m

Working With Pickle File

5m

Cross Sectional Momentum Strategy

10m

Calculate Average Dollar Volume

5m

Rank the Filtered Stocks

5m

Generate Buy Signals

5m

Compute Trading Cost

5m

Calculate Lookback Returns With Skip Days

5m

Paper/Live Trading Cross Sectional Momentum Strategy

10m

Annual Portfolio Selection

10m

Cross Sectional Momentum Additional Reading

2m
Fundamental Momentum

Fundamental factors such as revenues, earnings, operating income of the companies also cause momentum. Learn to create a cross sectional momentum based on the fundamental factor. Also, learn to combine multiple factors for creating a momentum strategy.

Fundamental Factors

10m

Gross Profit

2m

Frequency of Earnings Announcement

2m

Earnings Per Share

2m

Fundamental Momentum

3m 30s

Why Not Earnings?

2m

Which Stock to Short?

2m

Fundamental Momentum Strategy

10m

Calculate Operating Income

5m

Assign Rank to the Stocks

2m

Fundamental Momentum Additional Reading

2m

Test on Types of Momentum

12m
Event Driven Strategy

In this section, you will explain unscheduled and scheduled events in the trading world along with their examples. You will be able to analyse these events and identify the right tools to create trading opportunities.

Momentum Due to Unscheduled Events

2m 50s

Acquisition Effect on Momentum

2m

Accounting Scandal's Effect on Momentum

2m

Listing Unscheduled Events

2m

Profit From Unscheduled Event

2m

Momentum Due to Scheduled Events

3m 51s

Momentum Due to FED Meetings

2m

Momentum Due to Votes

2m

Longer PEAD in Conglomerates

2m

Listing Scheduled Events

2m

Event Driven Additional Reading

2m
Ranking Factors for Cross Sectional Portfolio

In this section, you will learn about factors which can be used for ranking assets in a portfolio. Some factors, such as value, complement the momentum strategy and some factors are found to be working for a long period of time.

Ranking on Other Factors

10m

Other Factors of Ranking Portfolio - I

2m

Other Factors of Ranking Portfolio - II

2m

Value and Momentum Relation

2m

Ranking Factors Additional Reading

2m
Treasury Markets

Treasury bonds are considered to be less risky than other asset classes. In this section, you will learn to create and backtest the momentum strategy in treasury markets. You will also explore the reasons which cause momentum and find the cumulative returns as well as the drawdowns.

Event Driven Strategy in Treasuries

4m 15s

Reasons for EOM Effect

2m

Problems of Average Returns

2m

Momentum in US Treasury Bond ETFs

10m

Average ETF Returns

2m

Last Day of Month

5m

Days From End of Month

5m

Generate Trading Signal

5m

Calculate Strategy Returns

5m

Plot Cumulative Curve

5m

Strategy Drawdown

2m

Strategy Performance

2m

Treasury Markets Additional Reading

2m

Test on Event Driven Strategies

12m
Momentum in Futures

In this section, you will learn about the need for futures. You will also learn about term structure or forward curves pertaining to futures markets. Thereafter, you will learn to extract roll returns by implementing a futures-spot arbitrage strategy.

Term Structure

2m 39s

Reasons for Contango

2m

What is a Term Structure?

2m

Is It Contango?

2m

Causes of Backwardation

2m

Which is More Common?

2m

Forward Curve

10m

Identify the Futures Contract

2m

Identify Term Structure

2m

Roll Returns

2m 38s

Formula for Roll Returns

2m

Roll Returns Extraction

10m

Calculate Roll Returns

5m

Generate Short Position Signals

5m

Lookahead Bias

1m 53s

Futures Market Additional Reading

2m
Cross Sectional Momentum Strategy in Futures

Futures spot arbitrage strategies have typical drawbacks. In this section, you will learn about these drawbacks. You will look at various solutions to go around these drawbacks. This will help you learn about concepts such as correlated assets. Thereafter, you will also implement a cross-sectional momentum strategy for commodity futures.

Issues With Future Spot Arbitrage

3m 47s

Issues With Buying Spot

2m

What If ETF and Spot Not Available?

2m

Cross Sectional Momentum in Commodities

4m

Avoid Adverse Spot Movement

2m

Term Structure and Momentum Relationship

2m

Cross Sectional Momentum Strategy in Futures Market

10m

Commodity Futures Ranking

2m

P&L Calculation in Continuous Futures

3m 19s

Correctly Rolled Continuous Futures

10m

Calculate Future Spot Ratio

5m

Calculate Future Spot Ratio Rank

5m

Set Deciles for Signals

2m

Cross Sectional Momentum in Futures Reading

2m

Test on Momentum in Futures

12m
Momentum Crashes

In this section, you will define the momentum crashes, the different stages in a momentum crash and, most importantly, how to shield your momentum portfolio from a crash.

Momentum Crashes

2m 57s

Momentum Crash Definition

2m

Occurrence of Momentum Crash

2m

Government Bailout on Loser Stocks

2m

Beta Index

10m

Avoiding Momentum Crashes

2m 32s

Scenarios in Momentum Crash

2m

High Beta Definition

2m

Risk Management Using Beta

2m

Momentum Crashes

10m

Momentum Crashes Additional Reading

2m
Automate Trading Strategies

This section deals with the steps required to automate the trading strategy for real trading using a broker's account. You will learn step by step guide to connect your trading strategy with the broker's account, fetch real and historical data, and place orders.

Automation of Strategy

10m

Tasks Required for Live Trading

2m

Application Programming Interface

2m

Connect Python IDE's to Broker's Terminal

2m

Sample Strategy to Run on Interactive Brokers

2m

Test on Momentum Crashes and Strategy Automation

10m
Risk Management

Even the best of strategies can ruin your capital if proper risk management is not in place. In this section, learn the return distribution of momentum strategies and apply risk management techniques such as stop loss and position sizing to protect your portfolio returns. Also, learn the importance of backtesting and getting familiar with different aspects of your trading strategy.

Risk Management

2m 25s

Risk Management Definition

2m

Risk Management Techniques

2m

Implementation of Stop Loss

2m

Objective of Positions Sizing

2m

Risk Management

10m

Risk Management Additional Reading

2m
Run Codes Locally on Your Machine

Learn to install the Python environment in your local machine.

Python Installation Overview

1m 59s

Flow Diagram

10m

Install Anaconda on Windows

10m

Install Anaconda on Mac

10m

Know your Current Environment

2m

Troubleshooting Anaconda Installation Problems

10m

Creating a Python Environment

10m

Changing Environments

2m

Quantra Environment

2m

Troubleshooting Tips For Setting Up Environment

10m

How to Run Files in Downloadable Section?

10m

Troubleshooting For Running Files in Downloadable Section

10m
Course Summary

This section includes a course summary and downloadable zipped folder with all the codes and notebooks for easy access.

Course Summary - II

2m 55s

Historical Data FAQs

5m

Python Codes and Data

2m

Trading Alphas: Mining, Optimisation, and System Design

Introduction

This course will serve as a step-by-step guide that helps you find the trades based on micro alpha opportunities in the markets today. The interactive methods used in this course will help you not only understand the concepts but also answer all questions about micro alphas. This section also covers the course structure as well as the various teaching tools used in the course, such as videos, quizzes, coding exercises, and the capstone project.

Introduction

3m 44s

Course Structure

2m

Quantra Features and Guidance

3m 48s

FAQs

2m
Micro Alphas

The efficient market hypothesis states that all information available to the market is contained in the current price. This creates a scenario where it would be impossible to consistently generate profits since the price movements are random and unpredictable. However, there exist ways to exploit market inefficiencies and make money. This section helps you take the first step towards studying micro alphas by establishing a baseline.

Micro Alphas

3m 12s

Efficient Market Hypothesis

2m

Overturn Efficient Market Hypothesis

2m

Autocorrelation

2m

Assumption of Technical Indicators

2m

How to Use Jupyter Notebook?

2m 5s

Generating Price Series at Random

5m

How to Use Interactive Exercises?

5m

Generate Random Numbers

5m

Scaling

5m

Generate Price Data

5m

Statistical Study on Randomly Generated Price Series

5m

Autocorrelation

5m

Trading Signals

5m

Why Did the Signal Fail?

5m

Additional Reading on Micro Alphas

2m
Market Inefficiencies: Trend

By employing some level of technical expertise, you too can stand a chance of benefiting from inefficiencies in the markets. Market trends are one of these inefficiencies. In this section, you will study how market trends take place. You will also learn how to formulate a strategy based on the relationship between past and current returns.

Market Inefficiencies

2m

Trends

3m 38s

Compounded PnL Curve

5m

Positive Auto-Correlation

5m

Positively Correlated Time Series

5m

Equation for Auto-Correlation

5m

Value of g

5m

Strategy for Positive Correlation

5m

Types of Backtesting

5m

Compounded PnL Curve

5m

Auto-Correlation

5m

Trending Prices

5m

Series of Returns

5m

Trend

5m

Generate Random Returns

5m

Linearly Fit the Autocorrelated Data

5m

Backtest the Strategy

5m

Additional Reading on Trends

2m
Market Inefficiencies: Mean Reversion

Is there a correlation between a stock's present and past returns that can point to its mean-reverting characteristics? The answer is yes. In this section, you will learn about the type of correlation that leads to mean reversion, how to form a strategy based on the mean-reverting properties of a stock, and also how to combine two strategies to get better results.

Mean Reversion

4m 25s

Market Characteristic

5m

Constant g

5m

Type of Time Series

5m

Correlation of Returns

5m

Strategy and Benchmark Returns

5m

Strategy Based on Correlation

5m

Ideal Metric

5m

Annualised Alpha

5m

Generate Negatively Autocorrelated Returns

5m

Additional Reading on Mean Reversion

2m
Trading with Trends and Mean Reversion

In this section, you will learn to create and backtest strategies around market inefficiencies such as trend and mean reversion using real-world data. You will also learn how to compare the strategy returns with the market returns to analyse its performance.

Trading with Autocorrelated Data

5m

Calculate Risk-Adjusted Returns

5m
Market Inefficiencies: Chart Patterns

Chart patterns are often used by traders to predict price movements. It's a type of market inefficiency that can be exploited to gain excess returns (alpha). In this section, you will learn how to backtest multiple patterns at the same time. You will also learn how to formulate a strategy based on the backtested results and assess its performance.

Chart Patterns

3m 55s

Define Chart Patterns

5m

Values of a Candlestick Pattern

5m

Backtesting

5m

Library for Candlestick Pattern

5m

Candlestick Pattern for Micro-Alpha

5m

Usefulness of Alpha

5m

Equity Asset Returns

5m

Chart Patterns

5m

Extract the Chart Pattern Function

5m

Chart Pattern Signals

5m

Calculate Signals

5m

Capital Allocation

5m
Market Inefficiencies: Correlation, Fundamental and Alternative

In this section, you will learn about a few types of market inefficiencies such as correlation, fundamental data, and alternative data. You will also learn how they impact the price movement and how they can be used to gain excess returns.

Correlation, Fundamental and Alternative

2m 52s

Correlation

5m

Usage of Correlation

5m

Cross-Sectional Correlation

5m

Fundamental Inefficiencies

5m

Inference for Correlation

5m

Insider Information

5m

Trading View based on Analyst Forecasts

5m

Golf and a Company's Performance

5m

Correlation

5m

Calculate Average Correlation

5m

Additional Reading on Correlation

2m
Market Inefficiencies: Cointegration

Cointegration is the basis of statistical arbitrage. In this section, you will learn how to implement a pairs trading strategy. You will also learn some of the traps of statistical arbitrage and how they can be avoided.

Cointegration

5m 39s

Alternative Term for Pairs Trading

5m

Predictive Model

5m

Trading the Spread Curve

5m

Spread Strategy Code

5m

Cash-Neutral Strategy

5m

Cointegration

5m

Hedge Ratio

5m

Cointegration

5m

Create a Spread

5m

Additional Reading on Cointegration

2m

Types of Market Inefficiencies

2m

Test on Micro Alphas and Market Inefficiencies

16m
Time Series Alphas

There are multiple sources of alphas, and the best known, as well as the most widely used alpha is the time-series alpha. This section will help you generate alpha with signals along the time axis. You will learn how you can use historical time series data to create an RSI-based strategy.

Time Series Alphas

3m 50s

Categories of Alpha

5m

Time Series Alpha

5m

Types of Alpha

5m

Problem with Independent Signals

5m

Number of Signals

5m

Positions for Time-Series Alpha

5m

Trading Logic

5m

RSI Less than 40

5m

Shift Returns

5m

PnL Curves

5m

Strategy vs Benchmark

5m

Factor in Time-Series Alpha Calculation

5m

RSI Strategy Logic

2m

Implementation of RSI Based Trading Strategy

5m

Calculate RSI

5m

Generate Signals Using RSI

5m

Calculate Portfolio Returns

5m

Additional Reading on Time Series Alphas

2m
Live Trading on Blueshift

Learn how you can take your backtested strategy live with some important steps. Learn about the code structure, the various functions used to create a strategy, and finally, paper or live trade on Blueshift.

Uninterrupted Learning Journey with Quantra

2m

Section Overview

2m 19s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Blueshift Code Structure

2m 57s

Important API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

Backtest and Live Trade on Blueshift

4m 5s

Additional Reading

10m

Blueshift Data FAQs

10m
Live Trading Template

This section includes a live trading strategy template that uses the RSI indicator to generate entry and exit signals. You can tweak the code by changing securities or the strategy parameters. You can also analyse the strategy's performance in more detail.

Paper/Live Trade Using RSI

2m

FAQs for Live Trading on Blueshift

5m
Cross-Sectional Alphas

Alphas can be generated not just with signals along the time axis, but also with signals along the instrument axis. In this section, you will learn to generate alpha by ranking assets based on their momentum along the instrument axis.

Cross-Sectional Alpha

2m 38s

Common Attribute

5m

Axis for Cross-Sectional Alpha

5m

Arrange in Order

5m

Indicator for Trading Signals

5m

Sum of Rows

5m

Two Ranks

5m

Cross-Sectional Approach

5m

Cross-Sectional Momentum Strategy Logic

2m

Cross-Sectional Momentum Strategy

5m

Calculate Momentum

5m

Backtest Cross-Sectional Momentum Strategy

5m

Calculate PnL

5m

Additional Reading on Cross-Sectional Alphas

2m

Paper/Live Trade Using Cross Sectional Alpha

2m
Timing Alphas

Putting on trades at the right time, hour, weekday, or month can be a significant source of alpha in some cases. In this section, you will learn about the importance as well as the impact of timing the alpha. You will also implement the concepts in a Jupyter notebook.

Timing Alpha

2m 18s

Source of Alpha

5m

Daytime vs Overnight Returns

5m

Persistent Overnight Returns

5m

MA Weekday Strategy

5m

Advantages of Weekday Strategy

5m

Important Timing Events

5m

Timing Alphas

5m

Calculate Overnight Returns

5m

Inference of Cumulative Returns Plot

5m

Use of Timing of Alphas

5m

Additional Reading on Timing Alphas

2m

Most Suitable Alpha

3m 52s
Combinations of Alpha

Is it possible to combine the different categories of alphas to create a trading strategy? Yes, in this section, you will learn about the various combinations of alphas. You will also implement a volatility-based trading strategy.

Combinations of Alpha

1m 35s

Combinations of Alpha

5m

Alpha Combinations-I

5m

Annualised Volatility

5m

Alpha Combinations-II

5m

Volatility Strategy

5m

Upper and Lower Limit

5m

Upper and Lower Limit Inference

5m

Volatility Based Trading Strategy

5m

Calculate Volatility of Stock Returns

5m

Backtest Volatility Based Trading Strategy with Lower Limit

5m

Additional Reading on Combinations of Alphas

2m

Things to Keep In Mind While Combining Strategies

4m 15s

Paper/Live Trade Using Volatility

2m
Finding Micro-Alphas

For finding micro-alphas, creativity is an indispensable prerequisite, and even slight modifications to old ideas can often deliver great results. In this section, you will be introduced to the research paper “100 Formulaic Alphas" which was published by Kakushadze in 2015. You will learn about some of the alphas and implement them in a Jupyter notebook.

Finding Micro-Alphas

4m 19s

Other’s Ideas

5m

Alpha #3 Factor

5m

Alpha #3 and Alpha #57

5m

Ranking RSI Values

5m

Micro-Alphas From 101 Formulaic Alphas

5m

Calculate Alpha #6

5m

Additional Reading on Finding Micro-Alphas

2m

Test on Alphas

14m
Assessing Results

To understand how well your strategy is working, you need to do a full assessment of the strategy. While it is very important to develop an intuitive sense of the nature of what we are looking at on a chart, this is by no means sufficient for a full assessment. In this section, you will learn about the importance of combining different metrics, which will help you understand a variety of aspects of strategy performance.

Assessing Results

2m 19s

Prerequisite for Finding Micro-Alphas

5m

Combination of Alphas

5m

Number of Metrics

5m

Utility of Sharpe Ratio

5m

Strategy Performance

5m

Additional Reading on Assessing Results

2m

Most Ideal Performance Metric

5m 53s
Total Profit

In this section, you will learn about total profit, which is by far the simplest and the most used performance metric. You will learn about compounded and non-compounded as well as realised and unrealised profits. You will also implement these concepts in a Jupyter notebook.

Total Profit

3m 4s

Characteristics of Total Profit

5m

Features of Total Profit

5m

Differences Between PnL Curves

5m

Which Strategy is Riskier?

5m

Reinvestment of Profits

5m

Realised vs Unrealised PnL

5m

Drawbacks of Realised PnL

5m

Drawbacks of Total PnL

5m

Information Provided by PnLs

5m

Limitations of Total Profit

5m

Strategy Comparison

5m

Impact of Compounded PnL

5m

Realised Vs Unrealised Profits

5m

Realised PnL of a Strategy

5m

Additional Reading on Total Profit

2m
Sharpe and Sortino Ratios

The Sharpe ratio and Sortino ratios help you compare the risk-adjusted performance of different portfolios or trading strategies and determine the most feasible of them all. In this section, you will learn about the two ratios in depth and implement the same using Python.

Sharpe and Sortino Ratios

5m 33s

Risk-Adjusted Returns

5m

Calculate Sharpe Ratio

5m

Risk-Free Rate

5m

Exclude Risk-Free Rate

5m

Drawbacks of Sharpe Ratio

5m

Sortino Ratio

5m

Sharpe and Sortino Ratios using Python

5m

Implement the Sharpe Ratio

5m

Implement the Sortino Ratio

5m

Additional Reading on Sharpe and Sortino Ratios

2m
Profit Factor and Drawdown

The Sharpe or Sortino ratios are not suited to evaluate high confidence strategies that take less-frequent but highly profitable trades. In this section, you will learn about the profit factor, which is a good metric to use when we find such types of Alphas. Additionally, the drawdown metric can help us estimate how much we can expect to be underwater at any given time.

Profit Factor and Drawdown

3m 9s

Profit Factor

5m

Compare the Profit Factor

5m

Drawdown of a Strategy

5m

Drawdown Calculation

5m

Maximum Drawdown Comparison

5m

Profit Factor and Drawdown using Python

5m

Implement Profit Factor

5m

Additional Reading on Profit Factor and Drawdown

2m
Profit Per Trade

The profit per trade metric helps you understand the average value you can expect to win or lose per trade. In this section, you will learn about the correct approach for computing profit per trade and you will also learn to compute the same using python.

Profit Per Trade

4m 17s

Application of Profit Per Trade

5m

Computing Profit Per Trade

5m

Profit Per Trade

5m

Additional Reading on Profit Per Trade

2m
CAGR, Alpha, and Beta

In this section, you will learn about three popular metrics - CAGR, Alpha and Beta. CAGR helps us determine how much return our strategy is realistically able to generate annually. Alpha shows us how much of the strategy’s return is independent of the benchmark. And the Beta provides us with some insight into our exposure to the underlying market.

CAGR, Alpha and Beta

3m 30s

Compounded or Non-compounded?

5m

Annualise the Sharpe Ratio

5m

Evaluate the Skill of a Money Manager

5m

Initial Backtest

5m

CAGR, Alpha and Beta

5m

Additional Reading on CAGR, Alpha and Beta

2m

Test on Strategy Results

14m
Strategy Execution

You need to be aware of the assumptions you will be making in order to avoid spending time on strategies that are not feasible in the real world or are too costly or complex to implement. Through this section, we will discuss a number of such common assumptions that traders make and how we can deal with them. You will also learn about some interesting execution algorithms such as the arrival price algorithm that may help to enhance your execution performance.

Strategy Execution

3m 56s

Implicit Assumptions

5m

Shortcomings of Execution on Close

5m

Executing Large Quantities

5m

Slippage

5m

Limitation of Market-on-Close Order

5m

Arrival Price Algorithm

4m 20s

Execution on the Open

5m

Order Type for Arrival Price Algorithm

5m

Sources of Transaction Costs

5m

Additional Reading on Strategy Execution

2m
Micro-Alpha Portfolio

So far we have discussed how to research, test, evaluate and execute individual alphas. However, the great strength of the micro-alpha approach lies in the combination of many individual alphas. In this section, you will combine multiple alphas and create a combined alpha strategy.

Combining Alphas

2m 39s

Traditional Portfolio Management

5m

Micro-Alpha Approach

5m

Alphas

5m

Combining Alphas - I

5m

Generating Signals

1m 48s

Combining All Micro-Alphas

5m

Paper/Live Trade by Combining Micro-Alphas

2m
Portfolio Optimisation

In this section, you will analyse various portfolio optimisation techniques, such as manual optimisation and mean-variance optimisation, by practically applying them to the combined alpha portfolio.

Portfolio Optimisation

3m 58s

Rebalance the Weights

5m

Equal Portfolio Weights

5m

Efficient Frontier

5m

Optimisation

5m

Additional Reading

2m
Advanced Alpha Mining

In this section, you will learn about more advanced alpha mining concepts, such as system parameter permutation and optimisation.

Testing Robustness Across Parameter Space

3m 4s

Testing Robustness of Strategy

5m

Selecting Best Parameter Sets

3m 30s

Finding Best Parameter

5m

Possible Lookback Values

5m

Parameter Optimisation

5m

Simpson's Paradox

5m

Sharpe Ratios

5m

Lookback Periods

5m

Clustering Algorithms - I

5m

Clustering Algorithms - II

5m

SPP

5m

Additional Reading - I

2m

Additional Reading - II

2m
Machine Learning Alphas

In this section, you will learn about machine learning alphas.

Machine Learning Alphas

1m 58s

Classification

5m

ML Alphas

5m
Basics of Vectorized Backtest

Backtests can be done either with loops or in the vectorized format. While a vectorized backtest is relatively complex, the gains in execution speed are well worth the effort. A looped backtest might take hours to run a single backtest, which will be executed in minutes in the vectorized format. In this section, you will backtest a simple moving-average crossover strategy in the vectorized format.

Creating a Basic Backtest

2m 34s

Factors for Setting Exit Signals

5m

Number of Winning and Losing Trades

5m

Reason for High Number of Losing Trades

5m

Advantage of Stop-loss and Profit-take

5m

Implementation of Profit-take and Stop-loss

5m

Conversion of Long-Short to Long-Only Signals

5m

Creation of Vectorized Backtest

5m

Calculate the Moving Average Crossover

5m

Generating Long-Short Trading Signal

5m

Generating Long-Only Trading Signal

5m

Calculate the Cumulative Sum of Returns

5m

Calculation of Portfolio Returns

5m

Additional Reading

2m
Adding Vectorized Stop-loss and Profit-takes

How can you make a good strategy better? You can incorporate profit-take and stop-loss levels which will help your strategy withstand black swan events. In this section, you will backtest the moving-average crossover strategy before and after adding a stop-loss and profit-take.

Application Of Profit-Take And Stop-Loss Filters

3m 2s

Replacement of Short Signals

5m

Identification of Entry and Exit Points

5m

Inference After Difference of Consecutive Signals

5m

Code of Entry Date

5m

Region Between Profit Take and Original Signal

5m

Individual Trade Profit and Loss

5m

Impact of Profit-take and Stop-loss Filters

5m

Time Difference Before and After Application of PT/SL Filters

5m

Vectorized Backtest with Profit-Takes and Stop-Loss

5m

Additional Reading

2m
Impact of Profit Take and Stop Loss on Strategy

In this section, you will analyse the backtested strategy after adding stop-loss and profit-take, as well as look at different measures which can be taken to optimise your capital allocation in the strategy.

Strategy Analysis After Application of Profit Take and Stop Loss

2m 17s

Use Case of Vectorized Backtest

5m

Technique to Increase Strategy Returns

5m

Analysis After Application of PT and SL

5m

Test on Combined Alpha, Advanced Alpha Mining Concepts and Backtesting

14m
Designing a Trading System

At its heart, a trading system consists of various sub-processes which are inter-connected with each other and perform various tasks in order to execute a trade as per the strategy. To make sure everything works correctly, you cannot run these processes in sequential order. In this section, you will get a brief on three types of computing architecture, which are parallel, asynchronous and distributed computing. You will also delve deeper into parallel computing architecture.

Software Architecture in Trading Systems

1m 40s

Sequential Order Based Trading System

5m

Paradigms for Creation of a Trading System

5m

Build a Trading System

5m

Parallel Computing

2m 45s

Methods to Implement Parallel Computing

5m

GIL and Parallel Computing

5m

Effect of Multi-threading on Single Core

5m

Data Appended to Queue

5m

Market Data Reading

5m

Threads with Different Idle Times

5m

Execution of Parallel Threads

5m

Output of Parallel Threads Process

5m

Implementation of Parallel Computing

5m

Output for Thread in Parallel Processes

5m

Resource Sharing Between Threads

5m

Data Structure Shared Between Threads

5m

Initialisation of Threads

5m

Calculate Square of Datapoints Using Threads

5m

Additional Reading

2m
Asynchronous Computing

Asynchronous computing uses the concept of multi-threading to implement threads in a concurrent fashion. In this section, you will understand how to build an asynchronous computing-based trading system.

Asynchronous Computing

2m 51s

Python Package for Asynchronous Computing

5m

Difference Between Concurrency and Multi-threading

5m

Property of Asynchronous Loops

5m

Python Keywords for Concurrency

5m

Asynchronous Recursion

5m

Function of Sleep in Asyncio Package

5m

Implementation of Asynchronous Recursion

5m

Use of Concurrency

5m

Implementation of Asynchronous Computing

5m

Difference Between Asynchronous Computing and Threading

5m

Keyword to Run Method in Asynchronous Fashion

5m

Purpose of Await Keyword

5m

Additional Reading

2m
Distributed Computing

In this section, you will take the concept of parallel computing further and see how you can build a distributed computing architecture which communicates with different programmes which could be run in different systems as well. You will also build a sample trading system in Python using distributed computing.

Distributed Computing

2m 45s

Communication Between Systems and Programs Using Python

5m

Python Packages for Distributed Computing

5m

Request Based Client Server Module

5m

Subscriber Based Client Server Module

5m

Acknowledgement of Order Sent in Trading System

5m

Limitation of Message Queue

5m

Distributed Computing

5m

Additional Reading

2m
Importance of Logging and Storage

Often, a trader tends to ignore logging of messages which could have been used later for debugging as well as improving the trading strategy. In this section, you will learn how to create logging messages. Further, you will understand the storage requirements as well as the advantages and disadvantages of storing market data in raw and compressed formats.

Logging And Storage

4m 10s

Application of Logging

5m

Level of Logging

5m

Difference in Logging Levels During Backtesting and Live Trading

5m

Levels of Logging

5m

Set Logging Level

5m

Configuration of Logger in Notebook

5m

Modification of Logger in Notebook

5m

Logging for a Trading System

5m

Log Messages at Critical Level

5m

Conversion of Raw Data

5m

Reason for Storage in Raw Data Format

5m

Conversion of Raw Data at Regular Intervals

5m

Additional Reading

2m
Hardware Elements of a Trading System

In this section, you will look at the various types of hardware systems built for trading systems and analyse their pros and cons in terms of execution speed, latency, and computing resources.

Hardware of a Trading System

3m 30s

Focus During Selection of Hardware

5m

Selection of Cost-effective Hardware

5m

Selection of Hardware Based on Latency Requirements

5m

Selection of Hardware for Multiple Strategies

5m

Additional Reading

2m
Software Elements of a Trading System

When you build a trading system, it is important to separate the processes and understand how they are interacting with each other. Further, you will also have to select the right operating system according to your needs.

Micro-Services and Operating System

4m 26s

Micro-Alphas and Industry Sectors

5m

Combinations of Micro-Alphas Weights and Industry

5m

Separation of Tasks as Micro-Services

5m

Order of Task Performance

5m

Advantage of Task Separation in Trading System

5m

Advantage of Linux OS

5m

Presence of GUI and Trading Systems

5m

Selection of Operating System

5m
Testing and Version Control

A trading system is actually built with a number of components and processes. It is always easier to rectify an error while it is small than to set about rectifying it once the entire system is built. Thus, unit tests should be undertaken to make sure that your trading system does not falter due to certain reasons which could have been easily avoided. Further, you should also make sure the various packages used can be run with each other, which is where version control helps in documenting and understanding the processes.

Testing and Version Control

2m 12s

Elimination of Unexpected Downstream Failures

5m

Importance of Unit Tests in Trading Systems

5m

Tools for Version Control

5m

Implementation of Unit Testing

5m

Difference Between Yield and Return

5m

Number of Runs for a Unit Test

5m

Unit Test Scenarios

5m

Additional Reading

2m
Implementation of a Trading System

In this section, you will learn about the points that you should keep in mind before you begin with the development of a trading system. You will also learn about the components and structure of the system and how it has to be started.

Prerequisites for Implementing a Trading System

3m

Questions to Ask

5m

Developing Strategy Models

5m

Stopping the Program

5m

Architecture and Start-Up

3m 5s

Mock Exchange

5m

Portfolio Manager

5m

Starting Up the System

5m

Mock Exchange Servers

5m

Pooling Option

5m

Test on Designing and Implementation of Trading System

18m
Types of Servers

In this section, you will learn about the types of servers involved in a trading system, such as the data server, trading server, and execution server. You will also learn how these servers communicate and work with each other.

Data Server and Execution Server

2m

Data Server

5m

Subscriber and Data Source

5m

PUB/SUB Pattern

5m

Instrument Name

5m

Execution Server

5m

Price Data

5m

Auto-correlation

5m

Trading Server

2m

Class for Trading Server

5m

ZeroMQ Sockets

5m

REQ/REP Pattern

5m

Trading, Data, and Execution Servers

5m

Data Sockets

5m

Data and Execution Server

5m

Trading Server

5m

Mock Exchange

5m

Startup

5m
Trading Logic

This section talks about two important classes, trading logic, which contains a set of functions directly related to the trading actions and signals, which is the centrepiece of the entire platform and is responsible for signal generation.

Trading Logic

2m

Run Function

5m

Portfolio Manager

5m

Price Difference

5m

Signals

2m

Optimisation

5m

Trading Logic, Portfolio Manager and Signals

5m

Test on Servers and Trading Logic

14m
Testing and Operation

In this section, you will learn about the importance of testable code. You will also learn about the operational challenges one can face while running this kind of architecture, and how to overcome them.

Testing and Operation

2m

Testing

5m
Capstone Project

In this section, you will apply the knowledge you have gained in the course. You will pick up a capstone project where you will combine a range of Alphas.

Getting Started

2m

Problem Statement

2m
Run Codes Locally on Your Machine

In this section, you will learn to install the Python environment on your local machine. You will also learn about some common problems while installing python and how to troubleshoot them.

Python Installation Overview

1m 59s

Flow Diagram

10m

Install Anaconda on Windows

10m

Install Anaconda on Mac

10m

Know your Current Environment

2m

Troubleshooting Anaconda Installation Problems

10m

Creating a Python Environment

10m

Changing Environments

2m

Quantra Environment

2m

Troubleshooting Tips for Setting Up Environment

10m

How to Run Files in Downloadable Section?

10m

Troubleshooting for Running Files in Downloadable Section

10m
Summary

This section includes a course summary and downloadable zipped folder with all the codes and notebooks for easy access.

Summary

5m 6s

Course Summary and Next Steps

2m

Python Codes and Data

2m

Trading in Milliseconds: MFT Strategies & Setup

Introduction

Medium-frequency traders do not need expensive hardware in comparison to high-frequency traders. However, they are still faster in comparison to retail and low-frequency traders. This section introduces the course contents and a welcome address by Dr E P Chan. The interactive methods used in this course will assist you in not only understanding the concepts but also answering all questions about systematic options trading. This section explains the course structure as well as the various teaching tools used in the course, such as videos, quizzes, coding exercises, and the capstone project.

Course Introduction

4m 46s

Course Structure

2m

Course Structure Flow Diagram

2m

FAQs

2m

Quantra Features and Guidance

2m 38s
An Introduction to Market Microstructure

In this section, we will cover the key concepts of market microstructure.

Market Microstructure

05m 40s

Order Book

5m

Bid-Ask Spread

5m

Liquidity Makers

5m

Market Impact

5m

Importance of Bid-Ask Spread

5m
Need and Challenges of MFT

In this section, you will understand the different types of latency and the latency requirements for medium-frequency trading. Further, you will get an understanding of the challenges faced by medium-frequency traders.

Definition of MFT

2m

Latency and Trading Regimes

5m

Types of Latency

5m

Identification of Trader Based on Latency

5m

Definition of Order Submission Latency

5m

Definition of Order Status Latency

5m

Trading Frequency

5m

Why Should You Focus on MFT and its Challenges

2m

Hardware Requirements of MFT

5m

MFT Latency Tolerance

5m

Consequence of High Regulations on HFT

5m

Knowledge About HFT Strategies

5m

Games Played by HFT

5m

MFT Focus Areas

5m
HFT Gaming

Certain strategies employed by HFT firms are detrimental to the medium-frequency trader’s ability to generate revenue. One of these HFT strategies is called front-running. This section covers the concept of front-running and its impact on medium-frequency traders.

Front-Running

2m

Reason to Be Wary of HFT

5m

Identification of Front-Running

5m

Effect of Front-Running on MFT

5m

Front-Running and Liquidity

5m

Additional Reading

2m
Ticking Strategy

In the world of trading at high speeds, every tick counts. A tick is a minimum change in the price of a security. In ticking strategy, HFT firms research and bid just one tick above the best bid to maximise their revenue. In this section, you will see if the ticking strategy works and how HFT firms use it to their own advantage.

Ticking Strategy

2m

Bid Price in Ticking Strategy

5m

Profitability of Ticking Strategy

5m

Factors to Consider in Ticking Strategy

5m

Ticking Strategy in Downtrend

5m

Interpretation of Bid and Ask Size

5m

Order Placement During Bid-Ask Imbalance

5m

Steps Taken When Ticking Strategy Fails

5m

Effect of Trend on Volatility

5m

Impact of Volatility on Ticking Strategy

2m

Use of Ticking Strategy

5m

Ticking Strategy in Volatile Markets

5m

Changes in Bid and Ask Volume

5m

Academic Research in Imbalance in Bid and Ask Volume

5m
Impact of Ticking Strategy

In this section, you will see the impact of the ticking strategy on medium-frequency traders. You will also get a glimpse of how dark pools can be used again by MFT traders.

Impact of Ticking Strategy on MFT

2m

Definition of Slow Market Makers

5m

Reason for No Order Fulfillment

5m

Definition of Adverse Selection

5m

Reason for Low Liquidity

5m

Use of Dark Pool Against MFT Traders

2m

Improvement of Order by Dark Pool Operator

5m

Execution of Sub-penny Ticking by MFT

5m

Execution of Sub-Penny Ticking

5m

Impact of Dark Pools on MFT

5m

Execution of Sub-penny Ticking by Dark Pool Operators

5m
Ratio Trade

Most markets operate on a first-come-first-serve basis. If your bid reached the exchange first, your bid would be executed first, and then other bidders with the same bid price would get their turn. But certain markets work on a pro-rata basis, where being first in line does not hold any special significance. In this section, you will see how HFTs use these markets to earn revenue with relatively less risk.

Ratio Trade

2m

Order Fulfillment in Time Priority Scenario

5m

Order Fulfillment in Pro-Rata Priority

5m

Advantage of Pro-Rata Priority for HFT

5m

Time of Order Placement in Pro-Rata Priority

5m

FAQ - Things to Keep in Mind

2m

Additional Reading

2m
Spoofing

Spoofing is an illegal practice where HFTs will place a large fake order to influence the market direction. Understand how this strategy is executed and why it is illegal.

Spoofing

2m

Impact of Total Bid Ask Volume on Price

5m

Spoofing Orders

5m

Execution of Selected Order

5m

After Execution of Spoofed Order

5m

Expectation After Cancellation of Large Order

5m

Extraction of Profit From Spoofing Orders

5m

Countering the Spoofing Strategy

2m

Reason for Illegality of Spoofing

5m

Call Bluff of Spoofing

5m

Reaction to Bluff Being Caught

5m

FAQ - Spoofing

2m

Additional Reading

2m
Other Ways HFT Wins

Research indicates that stop orders cluster around round numbers. Can someone take advantage of this fact? Understand how HFT and other market participants could force a large-scale trigger of stop orders. HFTs do not always focus on earning revenue by buying and selling or vice versa. They will also use certain orders to earn rebates, which are provided to market participants to provide liquidity. See how HFT firms earn rebates and impact medium-frequency traders.

Stop-Hunting

2m

Reason for Clustering of Stop Orders

5m

Execution of Stop Hunting

5m

Profit Through Stop Hunting

5m

Hide and Light Orders

2m

Conditions to Claim a Rebate

5m

Grant of Rebate

5m

Way to Earn Rebate

5m

Risk of Hide and Light Orders

2m

Speed of Data Feeds

5m

Lowering Risk of Hide and Light Order

5m

Impact of Same Latency of ITCH and SIP Feeds

5m

Additional Reading

2m
Thin NBBO Liquidity

Due to the various games which HFTs play, other market participants are wary of providing liquidity. In the process, they will place orders which are of only 100 shares sometimes. Learn how this impacts the backtesting of medium-frequency traders’ strategies.

Thin NBBO Liquidity

2m

Reason for Placement of 100 Quantity Shares

5m

Feasibility of NBBO Price for Backtesting

5m

Consideration of Factors for Effective Backtesting

5m

Test on Knowledge of HFT Gaming Practices

10m
An Overview of Types of Orders

HFTs employ a variety of order types for their gaming techniques, but certain order types can be optimised to counter these techniques. In this section, you will discover which order types can be used to build a defence by MFTs as well as which order types are used by HFTs for their gaming techniques.

Types of Orders

3m 15s

Define the Type of Order

5m

Order Type

5m

Defence Against HFTs

5m

Select the Order Type

5m
Immediate or Cancel Order

In this section, you will learn how to employ Immediate or Cancel (IOC) orders as a defence mechanism against HFT gaming strategies that cause toxic order flows and adverse selection

Immediate or Cancel Orders

4m 24s

IOC and Liquidity

5m

Market and Limit Order

5m

Adverse Selection

5m

Last-look Functionality

5m

Toxic Order Flows and Prevention of Adverse Selection

3m 46s

Impact of Adverse Selection

5m

Reason for Adverse Selection

5m

Toxic Order Flows

5m

Toxic Orders

5m

Last-look in Forex Markets

5m

FAQ on Immediate or Cancel Orders

2m

Additional Reading on IOC Orders

2m
Intermarket Sweep Order

In this section, you will learn about the mechanism of Intermarket Sweep Orders (ISOs). You will also learn the benefits that MFTs can gain by using this order type instead of a Non-ISO order type.

Pre-Reading on Intermarket Sweep Orders

2m

ISO and Regulation NMS

4m 42s

Rule 611

5m

Exception to Rule 611

5m

Intermarket Sweep Order

5m

ISO and Its Working

5m

Understanding ISO with an Example

3m 25s

Best Offer

5m

Average Price

5m

Non-ISO Drawbacks

5m

Additional Reading on Intermarket Sweep Orders

2m
ISO and Flash Crashes

Although ISOs can prove to be quite beneficial for MFTs, they are not free of limitations. This section explores the potential cautions of ISOs. It also studies certain theories behind the causes of flash crashes and the role of ISO in the occurrence of flash crashes.

ISO and Flash Crashes

6m 2s

Define a Flash Crash

5m

Cause of Flash Crashes

5m

One Cent Trades

5m

Stub Quotes

5m

Posting a Stub Quote

5m

ISO Execution

5m

Drawbacks of ISO

5m

FAQ on Intermarket Sweep Order

2m

Additional Reading on Flash Crashes

2m
Day ISO

While Day ISOs are usually used by HFTs, it’s important that we make ourselves familiar with this order type. In this section, you’ll learn about the uses of Day ISOs, how they work, and how they can be beneficial for HFTs. This section also compares Hide and Light orders with Day ISOs in order to clarify which order type is preferable and why.

Day ISO and Hide and Light Orders

3m 22s

Need for Hide and Light Orders

5m

Order Priority

5m

ISO and Day ISO

5m

Need for Day ISOs

5m

Benefits of Day ISO

5m

Additional Reading on Hide and Light Orders

2m
Dark Pools

Dark pools cover a substantial amount of transaction volumes. Therefore, it’s crucial for us to learn about this market. After completing this section, you will be able to define dark pools and explain their uses. You will also learn how market participants often abuse the system of dark pools and how you, as a trader, can avoid falling victim to such practices.

Use of Dark Pools

2m

Benefits of Dark Pools

5m

Dark Pool Orders

5m

Prices in Dark Pools

5m

NBBO and Dark Pool Liquidity

5m

Abuse of Dark Pools

2m

Midpoint Manipulation

5m

Order Execution

5m

Sub-Penny Trading

5m

Toxic Dark Pools

5m

Avoiding Toxic Dark Pool

2m

Measuring Adverse Selection

5m

Toxic Dark Pools

5m

Practices to Avoid Toxic Dark Pools

5m

Additional Reading on Dark Pools

2m

Test on IOCs, ISOs, Hide-and-Light, and Dark Pools

14m
Physics of MFT

What kind of infrastructure is needed to reduce the latency to 10 milliseconds? This section will cover three important things you will need to reduce the latency of your trading system.

Physics of MFT

2m 58s

Colocation

5m

Extranet

5m

ITCH Feed

5m

Virtual Private Server

5m

Advantage of ITCH Feed

5m

Live Trading Platforms

2m
Backtesting an MFT Strategy

This section explains the limitations of backtesting an MFT strategy. It also covers different aspects that an MFT trader should keep in mind while choosing a backtesting platform.

Backtesting an MFT Strategy

3m 2s

Purpose of Backtesting

5m

Order Execution Model

5m

Adverse Selection

5m

Backtest Gaming Strategies

5m

Choosing a Backtesting Platform

3m 54s

Language for Backtesting

5m

Scripting Language

5m

Special-Purpose Platforms

5m

API

5m

Backtesting Strategies

5m

FAQs on Choosing a Backtesting Platform

2m
Historical Tick Data

What are the different kinds of tick data? Where can you find the tick data for backtesting an MFT strategy? This section answers these questions by explaining the different kinds of tick data and discussing different sources for purchasing/renting historical data for backtesting an MFT strategy.

Historical Tick Data

5m 7s

Types of Tick Data

5m

Timestamp

5m

Calendar Spread Data

5m

Order Book Data

5m

Data in Tape Format

5m

Choosing a Data Vendor

5m

Additional Reading on Tick Data Vendors

2m

FAQs on Historical Tick Data

2m

Test on Backtesting, Historical Tick Data

14m
Order Flow Basics

In this section, you will learn the basics of order flow. This section also explains how order flow is used as an indicator.

Basics of Order Flow

2m 8s

Definition of Order Flow?

5m

Typical Structure of Order Flow Data

5m

Order Flow and Transaction Volume

5m

Calculate the Order Flow

5m

Order Flow as an Indicator

5m 9s

Order Flow Indicator

5m

Most Common Data Available

5m

Limitation of Ticker Tape Data

5m

ITCH Feed Data

5m

Aggressor Flag

5m

Best Order Flow Information

5m

Additional Reading for Order Flow Basics

2m

FAQs on Order Flow

2m
Calculate the Order Flow

This section explains the challenge of accurate order flow calculation. This section also discusses the tick rule and how to calculate order flow using the tick rule.

The Challenge of Accurate Order Flow Calculation

2m

Aggressive Traders

5m

Passive Traders

5m

Order Flow Calculation Accuracy

5m

Co-location for Order Flow Calculation Accuracy

5m

Advantage of Using ITCH Data

5m

Computing the Order Flow: Tick Rule

2m

Order Flow of Buy Market Order

5m

Basics of Tick Rule

5m

Order Flow of Sell Market Order

5m

Find the Order Flow Sign

5m

Method to Calculate the Order Flow

5m

Tick Rule for Order Flow Calculation

5m

Calculate the Tick Direction

5m

Ticks with Undefined Trade Direction

5m

Calculate the Order Flow

5m

Additional Reading for Order Flow Calculation

2m

Test on Basics and Calculation of the Order Flow

10m
Quote Rule and Lee-Ready Algorithm for Order Flow

This section discusses the quote rule and Lee-Ready Algorithm for order flow calculation. You will learn to implement the quote rule and Lee-Ready algorithm in Python.

Quote Rule and Lee-Ready Algorithm

4m 21s

Quote Rule for Computing Order Flow

5m

Buy Market Order

5m

Quote Rule for a Trade Above the Midpoint

5m

Drawback of the Quote Rule

5m

Lee-Ready Algorithm

5m

Lee-Ready Algorithm for Trades at the Midpoint

5m

Apply Quote Rule and Lee-Ready Algorithm

5m

Calculate the Midpoint

5m

Calculate the Trade Direction Using Quote Rule

5m

Additional Reading for Quote Rule and Lee Ready Algorithm

2m
Bulk Volume Classification

This section discusses Bulk Volume Classification (BVC) for order flow calculation. You will learn to implement the BVC method in Python.

Bulk Volume Classification

2m

Calculate Order Flow Using Bulk Volume Classification

5m

Data for Bulk Volume Classification

5m

Time Bars and Volume Bars

5m

Buy Volume

5m

Order Flow

5m

Calculate Time and Volume Bars

5m

Calculate the Volume Bars from Tick Data

5m

Bulk Volume Classification with Time Bars

2m

Gaussian CDF of Z-Score

5m

Calculate the Z-score of Price Change

5m

Bulk Volume Classification with Volume Bars

2m

Standard Deviation in the BVC Method

5m

Order Flow for Volume Bars

5m

Buy Volume for Volume Bars

5m

Calculate Order Flow with BVC

5m

Calculate the Order Flow Using The BVC Method

5m
Trade the Order Flow

In this section, you will learn to create trading strategies using the order flow. You will also create a strategy using the tick rule and backtest the strategy.

Trading the Order Flow

2m

Positive Order Flow

5m

Negative Order Flow

5m

Need for Order Flow Analysis

5m

Percentile-Based Order Flow Strategy

5m

Backtest The Order Flow Strategy

5m

Test on Calculating and Trading the Order Flow

14m

FAQ on Methods to Compute the Order Flow

2m
Capstone Project

In this section, you will undertake a capstone project. This project will require you to apply and practice the concepts learnt throughout this course.

Capstone Project: Getting Started

2m

Problem Statement

2m

Code Template and Data Files

2m

Capstone Project Model Solution

5m

Capstone Solution Downloadable

2m
Paper and Live Trading

To make sure that you can use your learning from the course in the live markets, a live trading template has been created which can be used to paper trade and analyse its performance. This template can be used as a starting point to create your very own unique trading strategy.

Steps to Set Up Alpaca Account and Get API Keys

2m

Template Code File

2m

Reducing the Latency

2m
Run Codes Locally on Your Machine

In this section, you will learn to install the Python environment on your local machine. You will also learn about some common problems while installing python and how to troubleshoot them.

Uninterrupted Learning Journey with Quantra

2m

Python Installation Overview

1m 59s

Flow Diagram

10m

Install Anaconda on Windows

10m

Install Anaconda on Mac

10m

Know your Current Environment

2m

Troubleshooting Anaconda Installation Problems

10m

Creating a Python Environment

10m

Changing Environments

2m

Quantra Environment

2m

Troubleshooting Tips for Setting Up Environment

10m

How to Run Files in Downloadable Section?

10m

Troubleshooting for Running Files in Downloadable Section

10m
Summary

In this section, we will summarise everything you have learned in this course.

Course Summary

5m 3s

Course Summary and Next Steps

2m

Python Codes and Data

2m

Advanced Momentum Trading: Machine Learning Strategies

Introduction

This section serves as a preview of the course and introduces the course contents. The interactive methods used in this course will assist you in not only understanding the concepts but also answering all questions regarding the use of machine learning algorithms for momentum trading. This section explains the course structure as well as the various teaching tools used in the course, such as videos, quizzes, coding exercises, and the capstone project. It also covers a few course-related frequently asked questions.

Course Introduction

4m 30s

Course Structure

2m

Quantra Features and Guidance

4m 9s

Course FAQs

2m
Revisiting Momentum

Momentum trading has been a widely tried and tested strategy, but what is it that drives momentum? In this section, we'll delve into what fuels momentum in the stock market and why it's a worthwhile approach to trading. Additionally, we'll provide a brief precap of the key concepts covered in the initial part of the course to ensure a solid foundation as we move forward.

Part Overview: I

2m

Momentum Trading

2m

Identify the Momentum Phenomenon

5m

Mutual Funds Redemption Request

5m

Nature of Momentum

5m

Events and Announcements

5m

Momentum in Commodities

5m
Getting Data: Single Asset

In this section of the course, you will learn how to fetch the data of a single asset. This data will then be used in the upcoming sections of the course to implement and backtest momentum trading strategies.

Uninterrupted Learning Journey with Quantra

2m

Getting Data: Single Asset

5m

Daily Price Data of Stocks

5m

Data Adjusted for Corporate Actions

2m
Time-Series Momentum

In this section, you will be taken through the traditional time-series momentum strategy. The strategy uses a fixed or a “static” threshold to generate buy and sell signals. After completing this section, you will be able to explain the rationale behind the time-series momentum strategy and you will also be able to implement the traditional time-series momentum strategy using Python.

Time-Series Momentum Strategy

2m

Time-Series Positions

5m

Past Performance in Time-Series

5m

Identify the Correct Order of Steps

5m

Predictor of Future Returns

5m

Trading Decision Based on Returns

2m

Essential Points for Momentum Trading

2m

Reason for Underperformance of Strategy

2m

Time-Series Momentum Strategy

5m

Calculate Yearly Returns

5m

Trading Rules

5m

Strategy Logic

5m

Hold Days

5m

Additional Reading on Time-Series Momentum

2m
Live Trading on Blueshift

This section will walk you through the steps involved in taking your trading strategy live. You will learn about backtesting and live trading platform, Blueshift. You will learn about code structure, various functions used to create a strategy and finally, paper or live trade on Blueshift.

Section Overview

2m 19s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Blueshift Code Structure

2m 57s

Important API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

Backtest and Live Trade on Blueshift

4m 5s

Additional Reading

10m

Blueshift Data FAQs

10m
Live Trading Template

To make sure that you can use your learning from the course in the live markets, a live trading template has been created which can be used to paper trade and analyse its performance. This template can be used as a starting point to create your very own unique trading strategy.

Paper/Live Trading TSMOM Strategy

2m

FAQs for Live Trading on Blueshift

5m
Transaction Costs and Slippage

The journey towards building a good strategy idea is incomplete without considering the transaction costs and slippages. In simple words, transaction costs encompass brokerage, commission, etc. Slippage is the difference between the expected and executed price. Learn these concepts and understand how to incorporate them into your strategy code.

Transaction Costs and Slippage

2m

Calculation of Transaction Cost

2m

Calculation of Slippage

2m

Verify Transaction Costs

5m

Slippage

5m

Estimating Slippage

5m

Implementation of Transaction Costs and Slippage

10m

Additional Reading

10m
Performance Analysis

To understand whether your strategy is working, you need to analyse certain metrics. In this section, you will learn how to evaluate the trade level metrics to depict how well the strategy has performed over a certain period of time, as well as evaluate the performance of your strategy based on returns, risk and both.

Generate Trade Sheet

5m

Trade Level Analytics

5m

Average Profit Per Winning Trade

5m

Win Percentage

5m

Average Trade Duration

5m

Additional Reading on Trade Level Analytics

2m

Performance Metrics

5m

CAGR

5m

Sharpe Ratio

5m

Maximum Drawdown

5m

Additional Reading on Performance Metrics

10m
Time-Series Momentum: Dynamic Threshold

Static thresholds for a time-series momentum strategy might not always be a suitable choice. This section covers the need for a dynamic threshold in the time-series momentum strategy and also the implementation of a dynamic threshold in the TSMOM strategy.

Time-Series Momentum With Dynamic Threshold

2m

Drawback of Static Threshold

5m

Dynamic Threshold

5m

Trading Decisions

5m

Positive and Negative Thresholds

5m

TSMOM Strategy with Dynamic Threshold

5m

Best Strategy

5m

Additional Reading on Dynamic Threshold TSMOM Strategies

2m

Test on Time-Series Momentum Strategy

10m
ML for Momentum Trading

Traditionally, momentum trading has relied on conventional methods for identifying trends and generating signals. However, in this age of machine learning, there's a growing need to explore its potential in enhancing the accuracy and efficiency of momentum trading. This section will take you through all the ways through which ML can be useful in momentum trading.

Part Overview - II

2m

Using ML for Momentum Trading

2m

Select the Advantage

5m

Changing Market Conditions

5m

Scaling Momentum Strategies

5m

Variable in Momentum Trading

5m

Relevance of Features

5m

Assigning Weights to Variables

5m

Adjustments Based on Market Conditions

5m

FAQs

2m

Additional Reading on the Need for ML in Momentum Trading

2m

Test on ML for Momentum

10m
Capturing Momentum Using ML

This section talks about the different types of ML models and the rationale behind choosing a classifier model to predict the momentum. It also takes you through the workings of the XGBoost classification model in detail.

Pre-Reading Document on Decision Trees

2m

Different Types of ML Models

2m

Predicting TSMOM

5m

Classification Model in Momentum Trading

5m

Predicting Continuous Responses

5m

Not a Classification Model

5m

XGBoost Classifier Model

2m

Composition of XGBoost Model

5m

Working of XGBoost Model

5m

Combining Weak Learners

5m

Incorrectly Predicted Data Points

5m

Stopping Criteria

5m

Additional Reading on XGBoost Model

2m
Implementation of XGBoost Classifier

A target variable is something that a machine learning algorithm tries to predict. And in order to do that, it requires input variables, which are called features. Once you have these, the next step is to split the dataset into training and testing sets and then finally train the model and make predictions. This section covers all these steps in detail, along with practical implementation in Python.

Target Variable

2m

Choose the Target Variable

5m

Features

2m

Use of Features

5m

Characteristics of Features

5m

Creating Features and Target Variable

5m

Create the Target Variable

5m

Calculate RSI

5m

Splitting and Scaling the Data

5m

Scaling the Data

5m

Scaling Timeline

5m

XGBoost Model

5m

Training a Model

5m

FAQs on XGBoost Classifier

2m
Metrics to Evaluate a Classifier

Until now, we have analysed the strategy based on performance metrics, like Sharpe ratio, drawdown, CAGR, etc. But how do we analyse the performance of the classifier? We can do that by checking the accuracy, recall and other metrics specific to the classifier. We will learn more about these classification metrics in this section.

Evaluating Classifier Model Effectiveness

2m

Accuracy of ML Model

2m

Interpretation of Accuracy

2m

Meaning of Confusion Matrix

2m

Interpreting Confusion Matrix

2m

Predicting Wrong Values

2m

False Positives in Confusion Matrix

2m

Beyond Accuracy

2m

Description of Precision

2m

Predicting Correct Signals

2m

Description of Recall

2m

Calculation of Precision

2m

Calculation of Recall

2m

Calculation of f1 Score

2m

Inference of Performance Metrics

2m

Metrics to Evaluate a Classifier

5m

Classification Report

5m

Additional Reading

10m
Selecting the Right Features

In machine learning, you have to strike a delicate balance between the number of features used to create a model, and the processing capabilities of the model itself. It would be great to have thousands of features but it will lead to complexity and higher computation time for the model. In this section, you will try to reduce the features while keeping an eye on the information lost as well.

Part Overview

2m

Selecting the Right Features

2m

Importance of Feature Selection

5m

Calculation of Feature Importance

5m

XGBoost and Feature Importance

5m

Decision to Remove Features

5m

Decision on Removal of Features

5m

Visualising Feature Importance with XGBoost

5m

Create an Instance of XGBClassifier

5m

Train the Model Using the Training Data

5m

Calculate Feature Importance

5m

Summary

2m
Reducing Features While Minimising Information Loss

Ranking Features in terms of their predictive power and then selecting the top features is one method to reduce features. However, this leads to information loss from the discarded features. Is there another method to reduce the features but to preserve as much information as possible? You will find out in this section.

Reducing Features While Minimising Information Loss

2m

Concern Regarding Feature Selection

5m

Suggestion to Minimise Information Loss

5m

Purpose of Autoencoder

5m
Application of Encoder for Multiple Features

An encoder takes multiple features and converts them into fewer features. In this section, you will understand how a neural network is used to create an encoder and preserve as much information as possible.

Application of Encoder in Reducing Features

2m

Purpose of an Encoder

5m

Implementation of Encoder Using Neural Network

5m

Calculation of Product of Weight and Input Feature

5m

Final Encoder Values

5m

Encoder Approach to Reduce Features

5m

Define the Input layer

5m

Define the Encoding Layer

5m

FAQs

2m
Application of Encoder and Decoder for Reducing Features

Assume that an encoder model converted 126 to 8 features. How can you examine if these 8 features contain the information of the original 126 features? In this section, you will use a decoder component as well so that you can check if the reduced features are a true representation of the original features. You will go through the concept and implement the encoder and decoder model in practice.

Application of Encoder and Decoder to Reduce Features

2m

Issue in Using Only Encoder

5m

Verification of Encoded Value

5m

Purpose of Training the Encoder

5m

Reduction of Features in Encoding and Decoding

5m

Expansion of Features

5m

Encoder-Decoder Approach to Reduce Features

5m

Training the Autoencoder Model

5m

Momentum Trading Strategy Using Encoder Features

5m

Additional Reading

2m

Summary

2m

Test on Reduction of Features

16m
Evaluating the ML Model with Cross-Validation

This section explores using cross-validation techniques to assess the performance of your model. Through practical demonstrations, you'll learn to evaluate the accuracy of the ML model. You will learn the step-by-step process of carrying out cross-validation with the help of Python.

Overview: Cross Validation and Hyperparameter Tuning

2m

Cross Validation

2m

FAQs on Cross Validation

2m

Correct Use of Cross Validation

2m

Purpose of Test Data

5m

Test Dataset

5m

Cross Validation Function

5m

Larger K-Value in Cross Validation

2m

Estimation of ML Model's Performance

5m

Rotation Estimation

5m

Standard Deviation of Cross Validation Scores

5m

K-Fold Cross Validation

5m

Additional Reading on Cross Validation

2m
Optimising the ML Model through Hyperparameter Tuning

This section takes you through the process of optimising the ML model by fine-tuning its hyperparameters. Hyperparameters play a critical role in determining the performance of the model, and tuning them effectively can enhance its accuracy and generalisation ability. You will also learn various techniques such as Randomized Search and Grid Search for hyperparameter tuning. By the end of this section, you'll be equipped with the skills to fine-tune your ML model effectively for improved results - all with the help of Python.

Hyperparameters

2m

Process for Best Hyperparameters

5m

Search Process for Hyperparameters

5m

Hyperparameter Tuning

2m

Identify the Technique

5m

Alternative to Grid Search

5m

Randomized Search vs Grid Search

5m

Randomized Search Effectiveness

5m

Identify the Process

5m

Hyperparameter Tuning

5m

Call the GridSearchCV Method

5m

FAQs on Hyperparameter Tuning

2m

Additional Reading on Hyperparameter Tuning

2m
Incorporation of Multiple ML Models

Multiple ML models, or ensemble models, typically use more than one ML model to produce the final predicted output. In this section, you will go through different types of ensemble models and their performance.

Part Overview

2m

Incorporation of Multiple ML Models

2m

Voting Classifier and ML Models

5m

Hard Voting Classifier Model

5m

Soft Voting Classifier Model

5m

Advantage of Voting Classifier Model

5m

Hard Voting Classifier Model

5m

Implement Hard Voting Classifier Model

5m

Soft Voting Classifier Model

5m

Implement Soft Voting Classifier Model

5m

Additional Reading

2m
Capstone Project 1

In this section, you will create a voting classifier machine learning model based trading strategy.

Getting Started

2m

Problem Statement

2m

Capstone Project Model Solution

2m
Validating Signals

This section focuses on validating momentum trading signals generated by the ML model. It acknowledges that certain aspects of the ML model's learning are beyond our control. Therefore, ensuring that the ML model generates only momentum signals becomes challenging. This segment explores a strategy that can help us validate and refine ML-generated signals.

Validating Signals

2m

Upward Trend Prediction

5m

Ensuring Momentum Based Signals

5m

Identify the Position

5m

Select the Best Course of Action

5m

Criterion for Short Position

5m

Validating Signals Strategy

5m

Merge the DataFrames

5m

Generate Signals

5m

FAQs on Validating Signals

2m

Test on Cross Validation, Hyperparameter Tuning, Multiple Models and Signal Validation

12m
Getting Data: Multiple Assets

In this section of the course you will learn how to fetch the data of multiple assets. This data will then be used in the upcoming sections of the course to build a cross-sectional momentum portfolio.

Getting Data: Multiple Assets

5m

Multi-Class Shares

5m
Revisiting Cross Sectional Momentum

In this section, you will learn the fundamentals of creating a cross-sectional momentum portfolio such as filtering stocks based on average daily turnover and ranking them based on the historical performance.

Part Overview on Cross-Sectional Momentum

2m

Introduction to Cross-Sectional Momentum

2m

Types of Momentum

5m

Momentum in Returns

5m

Which Lookback and Holding Period?

5m

Understanding Cross-Sectional Momentum Strategy

5m

Short-Term Momentum Analysis

5m

Long-Term Momentum Research

5m

Cross-Sectional Momentum Strategy

2m

Factor to Filter Stocks

5m

Steps for Cross-Sectional Momentum Strategy

5m

Long-Only Strategy

5m

Impact of High Number of Stocks

5m

Modify the CSMOM Portfolio

5m
Filter and Rank the Stocks

In this section, you will implement the filtering and ranking of stocks to create a cross-sectional momentum portfolio in Python.

Filter Stocks for a CSMOM Portfolio

5m

Calculate the Average Daily Turnover

5m

Filter the Stocks Based on Average Turnover

5m

Rank Stocks for a CSMOM Portfolio

5m

Calculate the Returns in Lookback

5m

Rank the Stocks Based on Lookback

5m

Additional Reading

2m

FAQs on Cross-Sectional Momentum (CSMOM) Strategy

2m
Implement Cross-Sectional Momentum Strategy

In this section, you will learn to implement the cross-sectional momentum strategy in Python once the stocks are filtered and ranked. You will not stop here, you will also learn to calculate and study the performance of the cross-sectional momentum portfolio.

Strategy Flow Diagram

2m

Create a CSMOM Portfolio

5m

Generate Signals for Long-Only Portfolio

5m

Generate Signals for Long-Short Portfolio

5m

Performance Analysis of a CSMOM Portfolio

5m

Stock Returns in the Holding Period

5m

Daily Returns of Assets in Portfolio

5m

Calculate Daily Portfolio Returns

5m
Capstone Project 2

In this section, you will apply the knowledge you have gained in the course. You will pick up a capstone project where you will create a long-only and short-only cross sectional momentum portfolios and compare their performance.

Problem Statement

2m

Capstone Solution

2m
ML-Based CSMOM Trading

In this section, you will learn the need to apply machine learning for the cross-sectional portfolio creation. This section also explains the steps required to apply machine learning.

Machine Learning For Cross-Sectional Momentum

2m

Advantage of ML for Trading CSMOM

5m

Purpose of Using ML

5m

Categorisation of Stocks

5m

Steps to Apply ML for CSMOM Portfolio

2m

Order of Steps to Apply ML for CSMOM Trading

5m

Defining Features

5m

Type of ML Model

5m

Position for Best Performing Stocks

5m

FAQs on ML-Based CSMOM Trading

2m
Features to Create ML-Based CSMOM Portfolio

In this section, you will learn to select the features for the machine learning model to create a cross-sectional momentum portfolio.

Features to Create ML-Based CSMOM Portfolio

2m

Cross-Sectional Momentum Strategy

5m

Factors

5m

Constructing the Features

5m

Momentum in Assets

5m

ML for CSMOM Portfolio

5m

Next Steps

5m
Select the ML Model

In this section, we will discuss the reason behind selecting the unsupervised learning algorithm to create an ML-based cross-sectional momentum portfolio.

How to Select the ML Model?

2m

Grouping Stocks

5m

Hierarchical Clustering

5m

Advantage of Clustering

5m

Partitioning a Dataset

5m

Advantage of Hierarchical Clustering

5m

Test on ML-Based CSMOM Portfolio

10m
What is Hierarchical Clustering?

In this section, you will learn the intuition behind the hierarchical clustering process and how grouping is done using this method.

What is Hierarchical Clustering?

2m

Clustering

2m

Correct Hierarchy

2m

Grouping Items

5m

Advantage of Hierarchical Clustering

5m

Hierarchical Structure

5m

Additional Reading

10m
Apply Hierarchical Clustering to Create CSMOM Portfolio

So far, you learnt the steps involved in implementing machine learning for creating a cross-sectional momentum portfolio. In this section, you will learn the practical implementation of hierarchical clustering to create CSMOM portfolio.

Hierarchical Clustering to Create CSMOM Portfolio

2m

Understanding Momentum Clustering

5m

Criteria for Momentum Clustering

5m

Clustering Method in the Course

5m

Methods of Stock Clustering

5m

Hierarchical Clustering Diagram

5m

Visualise the Clusters Using a Dendrogram

5m

Calculate Monthly Returns of Assets

5m

Create Linkage Matrix for Clustering

5m

Visualise the Dendrogram

5m

FAQs on Hierarchical Clustering for CSMOM Portfolio

2m
Challenges in Clustering

In order to apply hierarchical clustering to select stocks for a cross-sectional momentum portfolio, the clustering process needs to be customised to avoid challenges. In this section, you will learn about the challenges involved in clustering stocks to create a portfolio and methods to resolve them.

Challenges in Clustering

2m

Challenge of Hierarchical Clustering

5m

Bias in Portfolio Performance

5m

Issue of Single Stock Cluster

5m

Limiting Stocks per Cluster

5m

Customise the Clustering Process

5m

Ways to Customise the Clustering Process

5m

Limit the Number of Clusters

5m

Limit the Number of Stocks in a Cluster

5m
Create the CSMOM Portfolio after Clustering

After customising the clustering process and creating the cluster of stocks, the cross-sectional momentum portfolio can be created using the strategy rules. In this section, you will learn all about the strategy parameters and the process of selecting the parameters to create an ML-based cross-sectional momentum portfolio.

Create CSMOM Portfolio After Clustering

2m

Strategy Parameters for Cross-Sectional Momentum Portfolio

5m

Intermediate-Term Momentum for Momentum Strategy

5m

Portfolio Rebalancing in Cross-Sectional Momentum

5m

Position Sizing across the Portfolio

5m

Long and Short Positions in Cross-Sectional Momentum

5m

Create a CSMOM Portfolio Using Clusters

5m

Monthly Returns of Clusters

5m

Performance of Clusters in Lookback Period

5m

Calculate the Performance of a Portfolio

5m

Hierarchical Clustering for CSMOM

5m

Creating the Linkage Matrix

5m

Rebalancing a CSMOM Portfolio

5m

FAQs on CSMOM Portfolio

2m

Test on CSMOM Portfolio after Clustering

10m
Capstone Project 3

In this section, you will apply a machine learning based momentum strategy using all the concepts you have studied so far in the course.

Problem Statement

2m

Capstone Project Model Solution

2m
Run Codes Locally on Your Machine

Learn to install the Python environment in your local machine.

Python Installation Overview

1m 59s

Flow Diagram

10m

Install Anaconda on Windows

10m

Install Anaconda on Mac

10m

Know your Current Environment

2m

Troubleshooting Anaconda Installation Problems

10m

Creating a Python Environment

10m

Changing Environments

2m

Quantra Environment

2m

Troubleshooting Tips for Setting-up Environment

10m

How to Run Files in Downloadable Section?

10m

Troubleshooting For Running Files in Downloadable Section

10m
Live Trading on IBridgePy

In this section, you would go through the different processes and API methods to build your own trading strategy for the live markets, and take it live as well.

Section Overview

2m 2s

Live Trading Overview

2m 41s

Vectorised vs Event Driven

2m

Process in Live Trading

2m

Real-Time Data Source

2m

Code Structure

2m 15s

API Methods

10m

Schedule Strategy Logic

2m

Fetch Historical Data

2m

Place Orders

2m

IBridgePy Course Link

10m

Additional Reading

10m

Frequently Asked Questions

10m
Paper/Live Trading Template

To make sure that you can use your learning from the course in the live markets, a live trading template has been created which can be used to paper trade and analyse its performance. This template can be used as a starting point to create your very own unique trading strategy.

Template Documentation

10m

Template Code Files

2m
Summary

In this section, you will summarise the key concepts covered in the course and you will also go through the next steps that you should take after completing it.

Course Summary

2m

Summary and Next Steps

2m

Python Codes and Data

2m

about author

Dr. Ernest P. Chan

Dr. Ernest Chan is the Managing Member of QTS Capital Management, LLC., a commodity pool operator and trading advisor. QTS manages a hedge fund as well as individual accounts. He has worked in IBM human language technologies group where he developed natural language processing system which was ranked 7th globally in the defense advanced research project competition. He also worked with Morgan Stanley’s Artificial intelligence and data mining group where he developed trading strategies.

QuantInsti®

QuantInsti is the world's leading algorithmic and quantitative trading research & training institute with registered users in 190+ countries and territories. An initiative by founders of iRage, one of India’s top HFT firms, QuantInsti has been helping its users grow in this domain through its learning & financial applications based ecosystem for 10+ years.

Dr. Thomas Starke

Dr Thomas Starke is the CEO of the financial consultancy firm AAAQuants. With a remarkable career spanning working with Boronia Capital, Vivienne Court Trading and Rolls-Royce, he has worked on the development of high-frequency stat-arb strategies for index futures and AI-based sentiment strategy. As an academic, he was a senior research fellow and lecturer at Oxford University. A tech aficionado, he takes a keen interest in new technologies such as AI, quantum computing and blockchain. He holds a PhD in Physics from Nottingham University (UK).

Why quantra^®?

More in Less Time
Gain more in less time
Expert Faculty
Get taught by practitioners
Self-paced
Learn at your own pace
Data & Strategy Models
Get data & strategy models to practice on your own

User Testimonials

Vatsin Thaker

Student of MBA Finance, NMIMS, India

I found the course to be really helpful, as I have similar courses in my masters, I keep referring to the courses on Quantra. The module on Cointegration Test was really helpful to me in my project. I am a core finance student, and I have been practicing Python for a while. The python Jupyter notebook and the interactive exercise have really helped me get good command on python.

Luca Donghi

Portfolio Manager, FIA Asset Management, Italy

Very exhaustive, and the concepts are explained in a clear manner.

Michael Cuddehe

Commodity Trading Advisor, United States

I found the structure of the course to be very helpful. It has regular exercises included in it which are well designed. I have developed more familiarity & fluidity with coding because of this course. I was hoping to see concepts that I might be able to use & to my delight, I did come across these concepts, for example, resampling and combining the Daily and Monthly Timeframes in a data frame. This was something I found difficult in the past but now it seems I am able to gain the skills I need in order to do the kind of research I desire to do. I found the course very encouraging and I am pleased with it.

Sergei Belov

United States

Good overview of existing literature for combining alphas and an especially good section on execution.

Tan Kwan Hong

Senior Professor, Singapore

Excellent! Great knowledge!

Artur Barreiros

Professor at Instituto Superior Técnico, Portugal

Excellent and unique content.

Johann Smith

Analyst, Phoenix Group, South Africa

It is a good course

Yash Karia

India

Great Learning Experience

Po-yuan Chen

Taiwan

Satisfied with the coursework

Orestis Pardalis

Greece

My experience pursuing the course was great, I found the whole website to be very good. I was able to understand everything. When compared to other platforms, I notice that Quantra courses are very professional and to the point. I am very satisfied with the offering of this course.

Murali Padmanaban

United Kingdom

Understood various concepts behind HFT and MFT

Rafael Diaz

Technical Architect, United States

Good Learning Material

Robert Garza

Trader, United States

This course condensed a lot of deep information and presented it in a way that was easy to follow!

Donald Yang

Hong Kong

Good class and Good to learn.

Dileep Kumar

Senior Physiotherapist, India

Great to learn the concepts about Alpha.

Arturo Cruz Esparza

Director at FinSys Consultancy AS, Norway

Very good course that hand holds the student through the different concepts, both, of statistical tests and Python code.

Dylan Knights

Canada

My favourite course so far. Many ideas and concepts that I look forward to experimenting with.

Jeffrey Pancottine

United States

Great course, good detail and helpful tips.

Sean Lee

Taiwan

Insighful lecture of momentum trading strategy

Hin Fai, Eric Tsang

Hong Kong

This course described momentum strategy in a systematic way.

Steven Van Winkel

Quantitative Analyst at Tom Capital, Switzerland

This course covers all the main topics that are relevant to the markets. It serves as a very good introduction to the world of Algorithmic Trading. I liked the pace and the structure of the course. With 6 years of experience in the financial industry, I was able to refresh and strengthen my basics with the help of this course.

Ivan Yeo

Portfolio Manager, GIC Private Limited, Singapore

This course gives a good and layman's explanation of the concepts behind mean reversion, index arb and long-short strategies. The sample Python codes are a starting point for beginners to explore and test the concepts.

Alex Castro

United Kingdom

A really interesting overview of MR Strats, good for someone without much background in finance. Good prep for more advanced materials.

Faqs

Are there any webinars, live or classroom sessions available in the course?
No, there are no live or classroom sessions in the course. You can ask your queries on community and get responses from fellow learners and faculty members
Is there any support available after I purchase the course?
Yes, you can ask your queries related to the course on the community: https://quantra.quantinsti.com/community
What are the system requirements to do this course?
Fast-speed internet connection and a browser application is required for this course. For the best experience, use Chrome.
What is the admission criteria?
There is no admission criterion. You are recommended to go through the prerequisites section, be aware of skill sets gained and to learn the most from the course.
Is there a refund available?
We respect your time, and hence, we offer concise but effective short-term courses created under professional guidance. We try to offer the most value within the shortest time. There are a few courses on Quantra which are free of cost. Please check the price of the course before enrolling in it. Once a purchase is made, we offer complete course content. For paid courses, we follow a 'no refund' policy.
Is the course downloadable?
Some of the course material is downloadable such as Python notebooks with strategy codes. We also guide you to use these codes on your own system for you to practice further.
Can the Python strategies provided in the course be used immediately for trading?
We focus on teaching about quantitative and machine learning techniques and how learners can use them for developing their own strategies. You may or may not be able to directly use them in your own system. Please do note that we are not advising or offering any trading/investment services. The strategies are used for learning & understanding purposes and we do not take any responsibility for the performance or any profit or losses that using these techniques results in.
Are you using real time Stock market data in the course?
No. We do not take examples from 'real time data', but you shall be learning to code through historical data. Please do note that there is a section at the end that will guide you on how to automate for real time live trading. You can get more detailed learning on how to automate trading strategies through our free course, 'Automated trading with IBridgePy using Interactive Brokers Platform'.
Will I be getting a certificate post the completion of the programme?
Yes, you will get a certificate for each course separately within a few hours of completion of the course. The certificates are downloadable from your account tab "My Certificates".
What does "lifetime access" mean?
Lifetime access means that once you enroll in the course, you will have unlimited access to all course materials, including videos, resources, readings, and other learning materials for as long as the course remains available online. There are no time limits or expiration dates on your access, allowing you to learn at your own pace and revisit the content whenever you need it, even after you've completed the course. It's important to note that "lifetime" refers to the lifetime of the course itself—if the platform or course is discontinued for any reason, we will inform you in advance. This will allow you enough time to download or access any course materials you need for future use.
Is Python an essential skill for automated trading for beginners?
Python is not strictly essential for beginners in automated trading, but it is highly recommended. Here’s why:

Ease of Learning: Python has a beginner-friendly syntax, making it accessible even for those new to programming.

Versatility: Python is widely used in the finance industry for tasks like backtesting, data analysis, and building trading algorithms. Libraries like Pandas, NumPy, and TA-Lib make it easy to analyse financial data

Extensive Community Support: Python's popularity means a vast amount of tutorials, forums, and resources are available for troubleshooting and learning.

Integration with Broker APIs: Many brokers and trading platforms offer APIs with Python support, enabling seamless integration for order execution and real-time data analysis.

No Cost EMI

EMI starting from ₹10990/month for 6 months

Available through our partner NBFC

Premium Courses MIN 75% OFF

Specializations For MIN 75% OFF

Most Popular

Learning Track: Advanced Algorithmic Trading Strategies

Learn Advanced Trading Strategies

Skills Covered

Strategy Paradigms

Math & Core Concepts

Python Libraries

learning track 8

Advanced Algorithmic Trading Strategies

Course Features

Prerequisites

Advanced Trading Strategies Course

about author

Why quantra^®?

User Testimonials

Faqs

Learning Track: Advanced Algorithmic Trading Strategies

Our Cookie Policy