Learning Track: Machine Learning & Deep Learning in Trading Beginners
42 Hours
A highly recommended track for those interested in machine learning and its applications in trading. From data cleaning aspects to predicting the correct market trend and optimising AI models, these courses are perfect for beginners. Learn how different machine learning algorithms can be implemented on financial markets and create your own prediction algorithms using classification and regression techniques.
Level
FOUNDATION to INTERMEDIATE
Authors
QuantInsti®
Dr. Ernest P. Chan
Dr. Roger Hunter
Price Lifetime Access Limited Time Offer
₹23242/-₹25825/-
Original Price: ₹108194
76% OFF
+ Additional 10% OFF
- Live Trading
- Learning Track
- Prerequisites
- Syllabus
- About author
- Testimonials
- Faqs
Live Trading
Preprocess price data to resolve outliers, duplicate values, multiple stock classes, survivorship bias, and look-ahead bias issues.
List and implement common tasks in machine learning such as feature creation, training, forecasting, and evaluation in a step-by-step fashion.
Explain the concept of regression, hyper-parameter tuning and the use of gradient descent for cost function optimisation.
Use cross-validation to tune the hyper-parameters of a support vector machine.
Code a trading strategy to predict the next day's trend using a Support Vector Classifier.
Create a machine-learning trading strategy using Decision Trees and ensemble methods such as random forest and bagging.
Paper trade, analyse the strategies and apply them in live markets without any installations or downloads.
Skills Covered
Machine Learning
- Train and Test dataset
- Cross-validation and Hyperparameter tuning
- Support Vector Classifier
- CART, Boosting and Random Forest
Math & Core Concepts
- Regression and Classification
- Cost function optimization
- Accuracy, Recall and F1-Score
- Variance Score and R-Squared
Python Libraries
- NumPy, Pandas and Matplotlib
- Sklearn and TA-Lib
- Decision Tree Classifier
- Random Forest Classifier
- Support Vector Classifier
learning track 4
Machine Learning & Deep Learning in Trading Beginners
FOUNDATION
BEGINNER
INTERMEDIATE
Customize Cart
Total courses in cart: 0
Original Price
Slashed Discount
-
Subtotal
₹0
learning track
Machine Learning & Deep Learning in Trading Beginners
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.
Course Features
CommunityFaculty 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 be curious about the application of machine learning algorithms in financial markets. Prior experience in programming is required to fully understand the implementation of the machine learning algorithms taught in the course. If you want to be able to code and implement machine learning strategies in Python, then you should be able to work with 'Dataframes'. These skills are covered in the course 'Python for Trading: Basic'.
Syllabus
Introduction to Machine Learning for Trading
- IntroductionThis section introduces the topic of machine learning and goes on to explain where it can be applied. You will be guided through the detailed course structure and the various concepts covered in the course. You will also explore various features that are available to you on Quantra.
Welcome to Machine Learning!2m 45s
Course Structure2m 26s
Course Learning Outcomes44s
Quantra Features and Guidance3m 48s
- Machine LearningThis section focuses on explaining the terminologies used in machine learning such as training and testing data sets.Terminologies of Machine Learning1m 40s
True/not True About Machine Learning2m
Where to Apply Machine Learning?2m
Uses of Feature Selection2m
- Types of Machine LearningThis section explains the types of machine learning such as supervised learning, unsupervised learning, and reinforcement learning along with their applications in general and trading.Types of Machine Learning - Part 12m 58s
Types of Machine Learning - Part 255s
Dividing the Dataset2m
What is Not Supervised Learning?2m
What is a Regression Problem?2m
Types of Machine Learning2m
How Do Humans Learn?2m
How Not to Do Unsupervised Learning?2m
Where Does Clustering Belong?2m
Additional Reading10m
- Supervised LearningThis section covers the important models in supervised learning such as regression models, classification models, and artificial neural networks.How to Use Jupyter Notebook?2m 5s
Linear Regression10m
What is the Equation for Linear Regression?2m
Find the Predicted Price2m
Logistic Regression10m
Output of Logistic Regression2m
KNN Classification10m
KNN Algorithm2m
Support Vector Machine10m
What is Not a Support Vector Machine?2m
What is a Hyperplane?2m
Do You Know Machine Learning Models?2m
Random Forest10m
Do You Know Random Forest?2m
Artificial Neural Network10m
Output of an Artificial Neural Network2m
Additional Reading10m
Test on Basics of Machine Learning and Supervised Learning20m
- Unsupervised LearningThis section covers the unsupervised learning model known as K-Means clustering and its relevance in trading.K-Means Clustering10m
How Well Do You Know K-means?2m
Statistical Arbitrage2m
Additional Reading10m
- Reinforcement LearningThis section explains the third type of machine learning which is reinforcement learning. It covers the architecture of reinforcement learning and how it can be utilised in the trading world.Reinforcement Learning Example- Part 12m 44s
Reinforcement Learning Example- Part 22m 8s
What is Optimal Execution Price?2m
Assumptions of Reinforcement Learning2m
What is Optimal Action?2m
What is a Reward?2m
Reinforcement Learning10m
Additional Reading10m
- Predict Trend Using ClassificationThis section explains how to code and backtest a trading strategy using the machine learning classification algorithm. It demonstrates the backtesting of a trading strategy on S&P 500 index using the Support Vector Classifier algorithm in Python.Stock Market Prediction1m 56s
Assumptions of Prediction Model2m
Feature Identification2m
Classification Algorithm2m 27s
Support Vector Classifier Strategy10m
Frequently Asked Questions10m
Name the Algorithm2m
What Type of Data Did We Use?2m
Length of the Test Data2m
Getting Started5m
Import SVM Module5m
Read Data From CSV File5m
Target Variable2m
Create Classifier Model5m
Predict Trading Signals5m
Additional Reading10m
- Live Trading on BlueshiftThis 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 Quantra2m
Section Overview2m 19s
Live Trading Overview2m 41s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Blueshift Code Structure2m 57s
Important API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
Backtest and Live Trade on Blueshift4m 5s
Additional Reading10m
Blueshift Data FAQs10m
- Live Trading TemplateBlueshift Live Trading TemplateSupport Vector Classifier Strategy Template10m
FAQs for Live Trading on Blueshift10m
- Natural Language ProcessingThis section focuses on the introduction of natural language processing and its application in trading. It explains how machines get closer to a human level understanding of the text from sources such as news, social media, etc. This interpretation of the text is converted into sentiment score and further used to generate trading signals.Natural Language Processing10m
What is NLP?2m
Positive Sentiment Score2m
Financial Data2m
Additional Reading10m
- Data & Feature EngineeringThis section explains why it is extremely important to remove several issues from raw data such as survivorship bias, and duplicates before feeding data to the machine learning algorithm. Then it explains the features and labels to take from this data which help increase the predictive power of the algorithm.Data & Feature Engineering2m 48s
Importance of Data Quality2m
What is Feature Engineering?2m
Additional Reading10m
Test on Unsupervised Learning, RL, NLP and, Data and Feature Engineering12m
- Introduction to Generative AIThis section will explore the key principles of Generative AI, its capabilities, and its applications in trading.Section Overview2m
How does Generative AI work?2m
Main Capabilities of Generative AI2m
Applications in Finance2m
Case Study2m
Traditional ML vs Gen AI5m
Text Generation5m
Principles of Generative AI5m
Speech to Text Model5m
Summary2m
Additional Reading2m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Python Installation Overview1m 59s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- SummaryThis section concludes the course and provides a downloadable zipped folder with notebook and data file for easy access.Summary3m 23s
Frequently Asked Questions10m
Downloadable Code2m
Trading with Machine Learning: Regression
- Problem StatementThis is an introduction to the course which discusses the topics which will be covered further.
Getting Started1m 41s
Quantra Features and Guidance3m 48s
- Introduction to Data GenerationThis section explains how to generate and import data, how to use scikit-learn, and how to create useful indicators for prediction in the algorithm.Introduction to Scikit-Learn10m
Resizing the Data2m
Remove the NaN2m
Search the Hyperparameters2m
Importing Data1m 39s
Import Data and Drop Missing Values10m
Importing Libraries7m
Dropping Missing Values7m
Input Parameters2m 15s
Create Input and Output Parameters10m
Create a Moving Average2m
Move the Data2m
Creating Indicators7m
Recap2m 51s
- Data PreprocessingThis section specifies the importance of data pre-processing, demonstrates how to use Scikit-learn for data pre-processing, splitting the data into train and test, and fitting the regression function. It also includes important concepts like hyper-parameters, cross-validation, grid search, randomized search etc.
Creating X and Y Datasets4m 24s
Why Do Data Pre-processing?2m
Why Scale the Data?2m
Why Center the Data?2m
Data Preprocessing10m
Input/Output Datasets7m
Imputer Function7m
Concept of Pipeline and Steps10m
Why Use a Pipeline?2m
Concept of Pipeline10m
Creating Steps7m
Instantiating Pipeline7m
Hyperparameters3m 27s
Choose the Learning Model2m
What Are Hyperparameters?2m
Cross Validation, Test and Train5m
Tuning the Hyperparameters2m
How to Handle Grid Size?2m
Grid Search and Randomized Search4m 26s
Properties of a Grid Search2m
Which Search to Choose?2m
Cross Validation, Test and Train10m
Gridsearchcv Function7m
Train and Test Split7m
Fit Regression Equation7m
Recap of Data Pre-Processing2m 54s
Test on Generating and Pre-processing Data14m
- RegressionThis section delves into the types of machine learning regression, explains mathematical concepts behind regression function such as the gradient descent and cost function optimization, and demonstrates how to predict SPY movements.
Introduction to Linear Regression5m 57s
Linear Regression2m
Interpreting Regression2m
Errors and Residuals5m 31s
Types of Variation2m
Regression Application2m
Assumptions in Linear Regression10m
Assumptions of Linear Regression2m
Linear Regression10m
Solve the Regression2m
Calculate the Covariance2m
Cost Function and Gradient Descent4m 45s
How Does Gradient Descent Work?2m
Cost Function and Gradient Descent10m
Understanding the Cost Function2m
Do You Know Gradient Descent?2m
Multivariate Linear Regression2m
Linear Regression and Predicting GLD Movement10m
Best Fit Variable7m
Linear Regression7m
Calling Imputer Function7m
Predicting SPY Movement7m
Recap of Regression2m 54s
Additional Reading10m
- Bias and VarianceThis section provides information about the concepts of bias and variance, overfitting and underfitting, and regularization to optimize your models.Bias and Variance3m 24s
Bias or Variance?2m
Overfitting and Underfitting2m 58s
Overfitting is Caused By?2m
Failure of ML Algorithms2m
Concept of Regularization2m 35s
Lamda of Regularization2m
L2 Regularization2m
Recap Video2m 33s
- Applying the PredictionThis section explains how to apply prediction and assess the models.Prediction and Model Assessment1m 40s
Why Use Zero?2m
High of the Day Is?2m
Creating Column7m
Predict the Next Day's High and Low10m
Predicted High7m
Recap2m 24s
Test on Regression, Bias and Applying the Prediction20m
- Creating the AlgorithmThis section focuses on creating the algorithm and coding it in Python using the concepts learnt previously. It also explains log returns, signal generation, and Sharpe ratio to gauge the performance of the trading strategy.Trading Strategy3m
How to Use Jupyter Notebook?2m 5s
Frequently Asked Questions10m
Data Preparation10m
Data Preprocessing and Prediction10m
Strategy Analytics10m
Performance Analysis10m
Returns7m
Signal Generation7m
Sharpe Ratio7m
Recap2m 47s
- Live Trading on BlueshiftThis 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 Quantra2m
Section Overview2m 19s
Live Trading Overview2m 41s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Blueshift Code Structure2m 57s
Important API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
Backtest and Live Trade on Blueshift4m 5s
Additional Reading10m
Blueshift Data FAQs10m
- Live Trading TemplateBlueshift Live Trading TemplatePaper/Live Trading Regression Trading Strategy10m
FAQs for Live Trading on Blueshift10m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Python Installation Overview1m 59s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- Downloadable ResourcesThis section concludes the course and provides downloadable strategy codes and an e-book with the course contents.Python Codes and Data2m
Python for Machine Learning in Finance
- IntroductionMachine learning has myriad applications in various industries, including finance. In this section, you will acquaint yourself with the course structure, and the various teaching tools used in the course: videos, quizzes, and strategy codes. The interactive methods used help you to not only understand the concepts, but also how to implement the strategies.
- Machine Learning OverviewIn this section, you will understand how machine learning is used to solve problems which cannot be solved by traditional computer algorithms. You will also see its applications in different finance domains.
- Introduction to PythonThis 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 Quantra2m
Need for Python3m 7s
Preference for Python2m
Functionality of Python2m
How to Use Jupyter Notebook?2m 5s
Print Statement5m
My First Jupyter Notebook10m
Getting Started with Interactive Exercises5m
Operations and Functions in Python10m
Divide Two Numbers5m
Pandas Dataframe2m 22s
Function Call5m
DataFrame Axis Label2m
DataFrame and Basic Functionality10m
DataFrame Syntax2m
Dropping/Deleting Columns2m
Create Pandas DataFrame5m
DataFrame Indexing2m
Print Columns2m
Access Elements of a DataFrame5m
Add New Column to a DataFrame5m
Set Column as Index5m
Add Values of a Column5m
Additional Reading10m
- Financial Market Data and VisualisationAn 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 Data1m 44s
Correct Syntax for Importing Stock Data2m
Importing Time Series Data10m
Import Data from Yahoo! Finance5m
Data Visualisation10m
Plot Line Graph5m
Plot Bar Graph5m
Additional Reading10m
Frequently Asked Questions10m
- Machine Learning TasksBefore you start using the machine learning model, you have to train it first. In this section, you will go through the steps in creating a machine learning algorithm and how its performance can be calculated.Machine Learning Tasks3m 28s
Order of Machine Learning Tasks2m
Judging Performance of ML Model2m
- Target Variable and FeaturesA target variable is something that a machine learning algorithm tries to predict. And in order to do that, it requires input, which are called features. This section will explain the concept of target and features through examples. You will also learn how to create target and features for an ML algorithm.
Target Variable1m 59s
Choose the Target Variable2m
Pre Reading Material10m
Features4m 29s
Use of Features2m
Characteristics of Features2m
Features of an ML Model2m
Target and Features10m
Create a Target Variable5m
Calculate RSI5m
Calculate EMA5m
Check for Stationarity5m
Correlated Features5m
Additional Reading10m
Test on Machine Learning Applications and Tasks10m
- Machine Learning AlgorithmsThere are various types of machine learning algorithms. In this section, you will get an overview of each type of algorithm. You will also gain a basic understanding of which model to use for a particular problem statement.Machine Learning Algorithms10m
Model for Predicting Direction2m
Model for Predicting Price2m
Model for Computing News Sentiment Score2m
- Train-Test SplitThe train-test split is the technique of splitting the data into two parts. One part is used to train the ML model, and the other part is used to evaluate how well the model is making the predictions. You will learn the correct way of dividing time-series data for the train-test split.
Train-Test Split10m
Perform the Train-test Split5m
Test on Machine Learning Algorithms and Train-Test Splits10m
- Training & ForecastingThe model is trained on the training data and then it is used to make forecasts. In this section, you will learn how to use the training and testing data with a machine learning model. For illustration, we implement a Random Forest classification model in Python and use it to make predictions.
- Metrics to Evaluate ClassifierBacktesting is used to separate good strategies from bad ones. In this section, you will learn how to analyse the performance of your strategy on the historical data through backtesting. You will also learn to develop and backtest a trading strategy in Python. You will further calculate certain metrics like strategy returns, annualised returns and Sharpe ratio.Evaluating Classifier Model Effectiveness4m 27s
Accuracy of ML Model2m
Interpretation of Accuracy2m
Meaning of Confusion Matrix2m
Interpreting Confusion Matrix2m
Predicting Wrong Values2m
False Positives in Confusion Matrix2m
Beyond Accuracy4m 2s
Description of Precision2m
Predicting Correct Signals2m
Description of Recall2m
Calculation of Precision2m
Calculation of Recall2m
Calculation of f1 Score2m
Inference of Performance Metrics2m
Metrics to Evaluate a Classifier10m
Confusion Matrix5m
Classification Report5m
Additional Reading10m
Test on ML Algorithms and Metrics to Evaluate Classifier10m
- Introduction to BacktestingBacktesting is used to separate good strategies from bad ones. In this section, you will learn how to analyse the performance of your strategy on the historical data through backtesting.What is Backtesting?2m 22s
Backtesting Technique2m
Does Past Reflect Future?2m
How to do Backtesting?2m 24s
Steps in Backtesting2m
Evaluate the Performance of Backtesting2m
Need for Backtesting2m
Drawbacks of Backtesting2m
Strategy Backtesting10m
Strategy Returns5m
Annualised Returns5m
Sharpe Ratio5m
Additional Reading10m
- Live Trading on BlueshiftThis 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 Overview2m 19s
Live Trading Overview2m 41s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Blueshift Code Structure2m 57s
Important API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
Backtest and Live Trade on Blueshift4m 5s
Additional Reading10m
Blueshift Data FAQs10m
- Live Trading TemplateThis section includes a template of a trading strategy that can be used on Blueshift. The live trading strategy template is based on the strategy discussed in the course. You can tweak the code by changing securities or the strategy parameters. You can also analyse the strategy performance in more detail.Paper/Live Trading Random Forest Strategy10m
FAQs for Live Trading on Blueshift10m
- Metrics to Evaluate a RegressorAlong with the classifier model, you can also use the regression model to predict the target variables. In this section, you will be given a brief on linear regression and also how to analyse its performance by using the goodness of fit metric.
Goodness of Fit4m 10s
Why Goodness of Fit2m
Error of a Good Model2m
R-squared Value2m
Residual Plot2m
Pattern in Residual Plot2m
High R-squared Value2m
R-Squared10m
Calculate R-squared5m
Limitations of R-squared2m
Assumptions for Linear Regression10m
Highest R-squared2m
Linearity2m
Not an Assumption for Linear Regression2m
Autocorrelation2m
Residuals2m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Python Installation Overview1m 59s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- Course SummaryIn this section, you will go through the different concepts you learnt throughout the course. You will also be able to download all the strategy notebooks as a zip file. You can use these notebooks and modify their contents to create your own unique strategy.Course Summary3m 16s
Next Steps10m
Python Data and Codes2m
Data & Feature Engineering for Trading
- Introduction to the CourseIn this introductory section, you will learn the importance of data engineering and feature engineering which can be used either in your personal trading or in an institutional setting. Preprocessing of the financial dataset is essential to make it suitable for analysis. Extracting features from the datasets to feed into the machine learning algorithms, and setting the target variable for a particular ML problem increases the predictive power of your algorithm.
- Challenges in Financial Data EngineeringMost of the time, trading strategies look great while backtesting but fail to live up to the expectations during live practice. Incorrect financial data has the potential to produce inaccurate inferences. Failure in identifying the flaws in data makes it completely useless. Learn the six most common challenges in financial datasets.
- Exploratory Data Analysis in FinanceExploring the data helps to build familiarity with the data. After exploring the data, you will be able to describe what’s in the data and the characteristics of the data. It also helps you to identify the irregularities and anomalies and to discover the patterns and relationships in the data.
Closer Look At the Data2m 4s
Importance of EDA2m
Python Pickle2m
Adjusted Close Price2m
How to Use Jupyter Notebook?1m 54s
Working With Pickle File5m
Examining the OHLCV Data10m
Read a Pickle File5m
Find Null Values5m
Generate Descriptive Statistics5m
Irregularities2m 56s
Stock Classes2m
Minimum Value of Adjusted Close2m
Dataframe Profiling2m
Test on Challenges in Data engineering and Exploratory Analysis14m
- Survivorship Bias for Stock DataWe often backtest on the stock universe that survived until today and ignore the stocks that no longer exist. This causes survivorship bias in the backtesting. In this section, you will learn the concept of survivorship bias, why it is important to use survivorship bias-free data in the backtesting, and how to deal with it. Also, learn to identify delisted stocks from the stock universe.
- Redundant Stocks DataLearn to check for data redundancy. It is highly unlikely that two stocks or financial instruments will have the same prices across many dates. It can occur on a few dates coincidentally, but if it occurs across many numbers of dates and consecutively then something might be wrong with the data.Dealing With Redundant Stocks2m 43s
Effects of Redundant Data2m
Steps to Find Redundant Data2m
Handling Duplicate Stock Data10m
Create Stock Pairs5m
Compare the Stock Prices5m
Calculate Number of Duplicates5m
Reasons for Redundancy2m
- Multiple Stock Classes: One or All?A listed company can issue stock with multiple classes. These stock classes have different voting rights. Learn whether you should keep the data for all the stock classes or one. If one then which stock class to keep and which to remove.Dealing With Multiple Stock Classes2m 1s
One Stock Class2m
Stock Class2m
Retain All Classes2m
Multiple Stock Classes10m
Identify Stock Classes5m
Unique Symbols5m
- Outliers: How to Identify and Deal With Them?In this section, we talk about the outliers. An outlier is a data point that is significantly different from other data points. It can be due to data quality issues or can be real. Learn how to identify and deal with outliers.Dealing With Outliers2m
Outliers2m
Dealing With Outliers2m
Inflated Profits2m
Dealing With Outliers10m
Number of Trading Days With Zero Volume5m
Sort Dataframe by Returns5m
Test on Pre-Processing of Data14m
- News Data: Numerical FeaturesThis section covers how news data can be sourced, within the notebook, via webhose.io
Overview of the News Data1m 20s
Numerical Features2m 34s
Relevance2m
Novelty2m
Combine Numerical Features2m 15s
Combine Numerical Features2m
Calculate Feature Score2m
Aggregate News Items Daily2m
Numerical Features10m
Calculate Feature Score5m
Calculate Trading Date for Each Headline5m
Calculate Daily Feature Score5m
- News Data: Categorical FeaturesCategorical Features2m 9s
Categorical Features2m
One-Hot Encoding2m
Aggregating Categorical Attributes2m 16s
Aggregate Categorical Features2m
Issues With Mean Aggregation2m
Limitations of One-Hot Encoding2m
Aggregating Categorical Features10m
One-Hot Encoding5m
Aggregate Using Mean5m
Recap1m 44s
- Structural Breaks in Financial DataSometimes there is an unexpected and prolonged change in the structure of the time-series data. This leads to a structural break. Learn to identify structural breaks in the sentiment data and list the probable solutions to deal with that.Structural Breaks2m 48s
Structural Breaks in Time Series Data2m
Dealing With Structural Breaks2m
Effects of Structural Breaks2m
Test on News Data and Structural Breaks16m
- Fundamental Data: Merge Them CorrectlyThis section covers the merging of fundamental data of two popular data sources, sharader and WSH. Although these sources are not free, the notebook also elaborates on what the data looks like and how to parse it.Precap of Fundamental Data2m 58s
Sources of Fundamental Data3m 18s
Sharadar Data2m
Announcement and Filing Date2m
Actual Vs Expected Earnings Date2m
Sharadar Data10m
Dimension Fields2m
Why Dimension Fields?2m
Wall Street Horizon Data10m
Which Format?2m
Examining the Data2m 18s
Challenges in the Datasets2m
Identify the Issues2m
Multiple EPS Values2m
Challenges in Merging Dataset1m 5s
Common Tickers2m
Investigate the Issues2m
Test on Merging of Fundamental Data16m
- Look-ahead Bias: Deceptive ReturnsGet introduced to the issues of and scenarios where data from the future is used for backtesting. This leads to deceptive returns while testing. Learn about ways to get around this ubiquitous bias or problem.
Futures Prerequisite10m
Futures Contract2m
Margin Requirements2m
Settlement Price2m
Roll Return2m
Calculate the Roll Returns2m
Look-ahead Bias in Futures3m 9s
What is Look Ahead Bias?2m
Good Results2m
Futures' Mean2m
Remove Bias2m
Calendar Spread Strategy Prerequisite10m
Calendar Spread2m
Disadvantages of CS Strategy2m
Look-ahead Bias in CS Strategy2m
Problem With Two Instruments2m
Solving the Problem2m
Illiquid Futures2m
Bid-Ask Time Quote2m
Liquid Futures2m
- Types of Bars: Features ExtractionThe market transaction data can be sampled in a variety of ways. For example, time, number, volume and value of transactions are different data features that can be used. But some ways might be more useful than others. Get introduced to the criteria which can be used to sample the transaction data. Also, learn about how these bars differ in their statistical properties.Tick and Time Bars3m 20s
True for a Bar2m
Difference Between Time and Tick Bar2m
Limitation of Time Bar2m
Creating Time Bars10m
Resample Price Data5m
Calculate Open Price of Time Bar5m
Calculate Total Volume of Bars5m
Creating Tick Bars10m
Aggregate Price Data5m
Aggregate Volume Data5m
Volume Bars2m
Limitations of Volume Bars2m
Volume Bar2m
High Value of Volume Bar2m
Limitation of Tick Bar2m
Creating Volume Bars10m
Create New Group ID5m
Dollar Bars1m 48s
What Are Dollar Bars?2m
Identical Bars2m
Advantages of Dollar Bars2m
Creating Dollar Bars10m
- Information Bars: Market Order ImbalancesIn this section, you will get introduced to some of the advanced ways used to sample transaction data based on market order imbalances. You will also learn market imbalances and run bars and its implementation.Information Bars2m 22s
Measure of Information2m
Imbalance Bar2m
Difference Between Run and Tick Bars2m
Imbalance Bars10m
Calculate Rolling Imbalance5m
Additional Reading10m
Types of Bars12m
- Data Labelling for Better OutcomesSupervised machine learning algorithms need either of the two, input and a label to learn nuances of real data. In financial time series, the input is generally a window of price data. Whereas, ground truth or labels need to be explicitly generated based on the position that needs to be taken. Learn various methods like fixed time-horizon and triple barrier methods that can be used to label your data.Fixed-Time Horizon3m 28s
ML Paradigm Labelling2m
Labelling Fixed Threshold2m
The Fixed-Time Horizon Method10m
Calculate Future Returns5m
Labelling the Target Class2m
Calculate Daily Returns5m
Calculate Rolling Standard Deviation5m
Triple Barrier Method2m
Fixed-Horizon V/s Triple-Barrier2m
Calculating Horizontal Bars2m
Horizontal Bars and Volatility2m
Finding the Target Class2m
Vertical Bar2m
The Triple Barrier Method10m
Calculate Daily Returns5m
Call Triple Barrier Method5m
- Why Stationary Features?The right input into a machine learning model can make all the difference in the world. Learn about the need for stationary features. Decipher the price level information vs stationarity tradeoff. Learn about fractional differentiation to create effective features.Dealing With Features Selection3m 10s
Price Series2m
Series Stationarity2m
Inferential analysis5m
Adjusted Close Price2m
Fractional Differentiation10m
Concept of Fractional Differentiation5m
Dilemma5m
Calculating Binomial Distribution Weights2m
Calculate the ADF Statistics5m
Test on Data Labelling and Stationary Features14m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Uninterrupted Learning Journey with Quantra2m
Python Installation Overview2m 18s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- SummaryThis section consists of the summary of the course along with the downloadable files which include the data modules as well as the strategy notebooks.Summary2m 50s
Downloadable Code2m
Decision Trees in Trading
- Introduction To Decision TreesThis section introduces the topic and explains the basic structure of a decision tree. It also covers the concept of Decision Tree Inducers.
Introduction4m 11s
Quantra Features and Guidance3m 48s
Introduction To Decision Trees3m 24s
Types Of Decision Trees2m
Variables Of A Classification Tree2m
Prediction With A Classification Tree2m
Decision Tree Inducers2m 49s
Split Parameter In A Decision Tree2m
Leaf Parameter In A Decision Tree2m
Greedy Approach In A Decision Tree2m
Depth Of A Decision Tree1m
Test on Introduction To Decision Trees14m
- Splitting, Stopping and Pruning MethodsThis section describes some of the splitting measures like Gini Impurity and Mean Squared Error. It also includes stopping and pruning measures.Splitting Measures5m 8s
Entropy At An Internal Node2m
Calculate Gini Index2m
Information Gain At An Internal Node2m
Loss Function5m
Stopping Criteria And Pruning2m 45s
Different Stopping Criteria2m
K-Fold Cross Validation Pruning2m
- Classification ModelIn this section, you will learn to develop and implement a classification model in Python code.
Classification Decision Tree Model - Part 13m 31s
Splitting The Data2m
Using Balanced Class Weights2m
Classification Decision Tree Model - Part 23m 19s
Identify The Pure Node2m
Rule That Leads To A Pure Node2m
Classification Report2m
How to Use Jupyter Notebook?2m 5s
Classification Decision Tree Model10m
Import Data5m
Define Predictor Variable5m
Compute Future Returns5m
Define Target Variable5m
Create Train Slice5m
Define Decision Tree Classifier5m
Fit And Make Predictions5m
Evaluate Model Performance5m
Class Weights In Decision Trees5m
Class Weights - 65m
Recap1m 28s
Graphviz Installation Steps10m
Test on Splitting, Stopping, Pruning Methods and Classification Model14m
- Live Trading on BlueshiftThis 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 Quantra2m
Section Overview2m 19s
Live Trading Overview2m 41s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Blueshift Code Structure2m 57s
Important API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
Backtest and Live Trade on Blueshift4m 5s
Additional Reading10m
Blueshift Data FAQs10m
- Live Trading TemplateBlueshift Live Trading TemplateClassification Decision Tree Strategy Template10m
FAQs for Live Trading on Blueshift10m
- Regression TreesIn this section, you will learn about regression trees and how to build a trading model using them. It demonstrates the Python code to implement this and also calculates the strategy returns.A Trading Model Using: Regression Trees4m 14s
Properties Of A Regression Trees2m
What Is Not True About A Regression Tree?2m
Stopping Conditions For The Regression Tree2m
Trading Rule Model In Regression Tree2m
Output Of Trading Model2m
Regression Tree Model10m 10s
Strategy Analytics10m
Sklearn Method To Create Regression Tree2m
Input To DecisionTreeRegressor2m
Function Used To Predict The Target Variable2m
Predict Signal5m
Strategy Returns5m
Sharpe Ratio5m
Regression Tree Strategy Template10m
Precap To Next Section1m 44s
Test on Regression Trees10m
- Parallel Ensemble MethodsThis section discusses ensemble methods like bagging, along with the Python code for the same. It also talks about the Random Forest algorithm which uses the ensemble method and also provides the Python code for the same.Bagging4m 37s
Parallel Ensemble Methods2m
Properties Of Bagging2m
Possible Outcome2m
Final Output Of The Ensemble Model2m
Bagging Model5m
Define A Bagging Model5m
Next Steps2m
Bagging Performance2m
Random Subspace And Random Forest1m 52s
Bagging Vs Random Subspace Methods2m
Random Forest Method2m
Ensemble Vs Standalone Methods2m
Random Subspace Method2m
What Does Random Subspace Method Reduce?2m
Random Subspace Model5m
Randomly Sample Features2m
Number Of Predictors To Use2m
Random Subspace5m
Random Forest Model5m
Not A Valid Parameter2m
Valid Parameters2m
Random Forest5m
- Sequential Ensemble MethodsThis section takes you through the concept of Boosting and how it works. It also explains about AdaBoosting and Gradient Boosting along with their Python codes.Boosting3m 8s
Overfitting Vs Underfitting2m
Properties Of Boosting2m
AdaBoosting Model5m
Maths Behind AdaBoost
AdaBoosting5m
Gradient Boosting Model5m
Gradient Boosting5m
Test on Parallel and Sequential Ensemble Methods14m
- Cross Validation and Hyperparameter TuningThis section delves into the advanced techniques like cross-validation and hyper-parameter tuning which can be used to enhance your existing prediction models or any other machine learning models.
Cross Validation2m 27s
Correct Use Of Cross Validation2m
Larger K-value In Cross Validation2m
K-Fold Cross Validation5m
Cross Validation Method2m
Number Of Folds2m
Cross Validation Score5m
Hyperparameters2m
Structural Choices In Machine Learning2m
Properties Of Hyperparameter2m
Hyperparameters Tuning5m 12s
Methods For Tuning Hyperparameters2m
Dimensionality Of The Grid Increases2m
Properties Of Grid Search2m
Hyperparameter Tuning10m
Randomized Search Vs Grid Search2m
Parameter To RandomSearchCV2m
Best Hyperparameters2m
Call A RandomizedSearchCV Method5m
Additional Reading10m
Test on Cross Validation and Hyperparameter Tuning14m
- Challenges in Live TradingThis section talks about the challenges faced during saving the model and data, and retraining the model. It demonstrates the simulation of trading using decision trees, and provides downloadable resources at the end of the course.Challenges in Saving Model And Data5m 46s
Pickle Parameter2m
Dump Command2m
Serialization2m
Save The Model2m
Save The Data2m
Challenges In Retraining The Model3m 26s
Retrain A Model2m
How To Perform Simulation3m 43s
Simulation Of Trading2m
Data Leakage2m
Trading Simulation Using Decision Trees10m
Course Summary2m 20s
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Python Installation Overview1m 59s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- Downloadable CodeDownloadable Code2m
Trading with Machine Learning: Classification and SVM
- IntroductionThis section presents the topic of machine learning classification, along with its types and applications. It covers technical indicators such as RSI, Parabolic SAR, and ADX.
Getting Started2m 34s
Quantra Features and Guidance3m 48s
What is Classification?6m 32s
Steps to Classify2m
Teaser on Classification2m
Types and Applications2m
Technical References10m
Importing Libraries5m
Technical Indicators - Part A3m 38s
Know Your Technical Indicators2m
Technical Indicators - Part B3m 23s
Applying Technical Indicators2m
Dropping Values5m
Creating An Indicator5m
Recap1m 45s
- Binary ClassificationThis section helps develop an understanding of binary classification, its uses and the math behind it. It also includes types of classifiers like sigmoid, tanh and gradient descent.What is Binary Classification?3m 16s
Types of Classification2m
How to Classify?2m
Uses of Binary Classification2m
The Math in Classification4m 46s
Decision Boundary10m
Equation of Classification2m
Choosing the Learning Rate2m
Applying Classification4m 12s
Binary Classification2m
Why Use Technical Indicators?2m
Recap54s
- Multiclass ClassificationThis section delves into the topic of multiclass classification and explains the concepts of one versus all algorithm, one-hot encoding, and Softmax Function. It also covers performance measures in machine learning.What is Multiclass Classification?4m 6s
Identify the Classification2m
Multiclass Classification2m
What is the One Vs All Algorithm?5m 51s
Which Class Does It Belong To?2m
One Vs All2m
Probability Concepts Part 110m
Probability Basics2m
More Probability2m
Probability Concepts Part 210m
Advanced Probability2m
Applying Probability2m
Performance Measure in ML10m
Define Accuracy2m
What is F1 Score?2m
One Hot Encoding and Softmax10m
Encoding2m
Recap56s
- Support Vector MachineThis section explains the concept of Support Vector Machine (SVM), the mathematics behind it, what support vectors are, and the parameters involved in SVM.What is Support Vector Machine?3m 59s
Mathematics Behind SVM10m
What Are Support Vectors?2m
Separating Data2m
The Parameters in SVM4m 2s
Degree As a Parameter2m
Effect of C2m
Recap42s
- Prediction and StrategyThis section involves the building of a predictive model using SVM, and an intraday trading strategy based on this predictive model. It includes the Python codes for the same and also helps in understanding the different hyper-parameters used for optimising algorithms and analysing the strategy performance.Code Overview10m
How to Use Jupyter Notebook?2m 5s
Trading Strategy Classification10m
Frequently Asked Questions10m
How to Prepare the Data?6m 29s
Data Resolution2m
What Are the Inputs?2m
Trimming the Data5m
Classifying the Returns5m
Modifying a Dataframe5m
Pipelines and Steps5m
Hyperparameter5m
Training and Fetching5m
Support Vector Classification5m
Testing and Predicting5m
Analysing the Performance5m
Recap1m 14s
FAQs on Live Trading10m
Test on Classification and SVM12m
- Live Trading on BlueshiftThis 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 Quantra2m
Section Overview2m 19s
Live Trading Overview2m 41s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Blueshift Code Structure2m 57s
Important API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
Backtest and Live Trade on Blueshift4m 5s
Additional Reading10m
Blueshift Data FAQs10m
- Live Trading TemplateBlueshift Live Trading TemplatePaper/Live Trading Classification Strategy10m
FAQs for Live Trading on Blueshift10m
- Live Trading on IBridgePySection Overview2m 2s
Live Trading Overview2m 40s
Vectorised vs Event Driven2m
Process in Live Trading2m
Real-Time Data Source2m
Code Structure2m 15s
API Methods10m
Schedule Strategy Logic2m
Fetch Historical Data2m
Place Orders2m
IBridgePy Course Link10m
Additional Reading10m
Frequently Asked Questions10m
- Paper and Live TradingIn this section, a live trading strategy template will be provided to you. You can tweak the strategy template to deploy your strategies in the live market!Template Documentation10m
Template Code Files2m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Python Installation Overview1m 59s
Flow Diagram10m
Install Anaconda on Windows10m
Install Anaconda on Mac10m
Know your Current Environment2m
Troubleshooting Anaconda Installation Problems10m
Creating a Python Environment10m
Changing Environments2m
Quantra Environment2m
Troubleshooting Tips For Setting Up Environment10m
How to Run Files in Downloadable Section?10m
Troubleshooting For Running Files in Downloadable Section10m
- Downloadable ResourcesThis section concludes the course and provides downloadable strategy codes and an e-book with the course contents.Python Codes and Data2m
about author
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. 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.
Dr. Roger Hunter
Dr. Roger Hunter is the Chief Technology Officer of QTS. He is responsible for designing high-performance automated execution system that achieved negative slippage. Roger is a serial entrepreneur, having founded profitable hedge funds and software firms. Roger was formerly professor of mathematics at New Mexico State University, and he obtained his Ph.D. in Mathematics from Australian National University.
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
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 EMIEMI starting from ₹4571/month for 6 months
Available through our partner NBFC
₹23242₹108194
