Learning Track: Portfolio Management and Position Sizing using Quantitative Methods
66 Hours
Learn to optimise the size of your trades, capital allocation in each of your strategies, and address the position sizing & portfolio management challenges using various quantitative techniques. Explore traditional factors like value, and unconventional factors like skewness. Apply winsorization, z-score standardisation for weight allocation. Learn AI and Ml-based techniques such as hierarchical risk parity (HRP), and LSTM and apply the concepts learnt in live markets (paper trade).
Level
BEGINNER to ADVANCED
Authors
QuantInsti®
Quantpedia
Dr. Thomas Starke
Price Lifetime Access Limited Time Offer
₹51700 /-₹64625/-
Original Price: ₹258494
75% OFF
+ Additional 20% OFF
- Live Trading
- Learning Track
- Prerequisites
- Syllabus
- About author
- Testimonials
- Faqs
Live Trading
Implement and backtest the position sizing methods such as CPPI, TIPP, and volatility targeting on an index reversal strategy.
Find and implement unconventional factors for generating alphas.
Construct factor-based portfolios using advanced methodologies like factor timing.
Apply simulation methods such as Bootstrapping and Monte Carlo.
Allocate capital using the Kelly criterion, modern portfolio theory, and risk parity.
Allocate weights to a portfolio based on a hierarchical risk parity (HRP) approach and learn different portfolio management techniques like IVP, EWP and CLA.
Allocate weights to portfolio using mean-variance optimisation, LSTM neural networks and create long only, long-short portfolios.
Paper trade, analyse the strategies and apply them in live markets without any installations or downloads. Also, implement all the concepts learned in capstone projects.
Skills Covered
Position Sizing
- Kelly, Optimal f
- CPPI, TIPP
- Volatility Targeting, MPT
- Fama, French Three Factor Model
- Mean-Variance Optimisation
Math & Core Concepts
- Treynor Ratio, Information Ratio
- Beta, Covariance
- Linkage Matrix
- Factor Timing, Factor Tilting
- Walk Forward Optimisation
Python Libraries
- NumPy
- Pandas
- Matplotlib, Seaborn
- Sklearn
- OLS, cvxpy,TA-lib
learning track 7
Portfolio Management and Position Sizing using Quantitative Methods
BEGINNER
INTERMEDIATE
Customize Cart
Total courses in cart: 0
Original Price
Slashed Discount
-
Subtotal
₹0
learning track
Portfolio Management and Position Sizing using Quantitative Methods
INTERMEDIATE
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
A general understanding of trading in the financial markets and knowledge of Python would be helpful. The learning curve could be steep if you are a beginner in both these skills. However, you can practice regularly with the hands-on learning exercises given in the course to gradually build the required skills. To learn how to use Python, check out our Free course "Python for Trading: Basics". You should also have a basic knowledge of machine learning algorithms and training and testing datasets. These concepts are covered in our free course 'Introduction to Machine Learning'.
Syllabus
Quantitative Portfolio Management
- IntroductionOverview of portfolio management using quantitative techniques.
Basics of Portfolio Construction Understand mathematical terms, such as covariance, returns and standard deviation of a portfolio, that are required to construct a portfolio.
Mathematical Terms for Portfolio Construction2m 54s
Calculate Covariance2m
Interpret the Covariance Value2m
Calculate Portfolio Returns2m
Calculate Portfolio Standard Deviation2m
How to Use Jupyter Notebook?2m 5s
Basics of Portfolio Construction10m
Calculate Portfolio Returns in Python5m
Calculate Covariance in Python5m
Calculate Portfolio Std Deviation in Python5m
Frequently Asked Questions10m
- Modern Portfolio TheoryCalculate optimal weights by maximising mean-variance of the portfolio. Maximize returns per unit risk of the portfolio choosing stocks with less covariance. Simulate random weights and plot the Efficient Frontier.
Construct Two-Stock Portfolio using MPT3m 46s
Objective of MPT2m
Choose the Portfolio Based on Covariance2m
Equi-Weighted Portfolio2m
Efficient Frontier2m
Targeted Risk2m
Implement Modern Portfolio Theory in Python10m
Choose the Portfolio - MPT2m
Plot the Efficient Frontier2m
Calculate Optimal Weights5m
Construct Multiple Stocks Portfolio using MPT10m
Returns of Portfolio with Multiple Stocks2m
Portfolio Standard Deviation - Matrix Form2m
Covariance Matrix2m
- Kelly CriterionApply the Kelly Criterion to optimise the capital allocationWhat is Utility?2m 2s
The concept of Utility2m
The Utility Curve2m
The Kelly Criterion2m 13s
The Kelly Criterion: Derivation10m
The Final Portfolio Value2m
The Daily Portfolio Value2m
Create a Portfolio Based on Kelly Criterion10m
Create an Array of Weights5m
Calculate the Final Portfolio Value5m
Create the Kelly Criterion5m
Create a Kelly Portfolio5m
- 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 Kelly Criterion Strategy10m
FAQs for Live Trading on Blueshift10m
- Risk ParityAllocate capital to the securities in the portfolio such that each security contributes equally to the overall risk of the portfolio.Construct Two-Stock Portfolio using Risk Parity2m 28s
Risk Parity Approach2m
Basis of Risk Parity2m
Calculate Percentage Capital Allocation2m
Risk Parity10m
Calculate Weights using Risk Parity Approach5m
Portfolio with Multiple Stocks10m
Risk Parity for Multiple Stocks5m
Data Handling5m
Extension to 'n' Stocks5m
Portfolio Metrics5m
Sharpe Ratio5m
Risk Parity Relationship2m
Risk Parity vs Traditional Portfolio2m 27s
Risk Parity Failure2m
Test on Capital Allocation12m
- BetaUnderstand and interpret beta of an asset. Calculate beta of an asset using different methods.What is Beta?3m 28s
Risk Exposure2m
Market Beta2m
Interpretation of Beta2m
Movement of Asset with Positive Beta2m
Movement of Asset with Negative Beta2m
Beta of an Asset in Python10m
Calculate Daily Returns5m
Calculate Beta5m
- Capital Asset Pricing Model (CAPM)Understand the Capital Asset Pricing Model and its limitations. Calculate expected returns of an asset using the capital asset pricing model.Introduction to CAPM2m 32s
Factors Affecting Expected Return2m
Calculate Expected Return on Asset2m
What is Security Market Line?2m 50s
SML Characteristic2m
Stocks lie on the SML2m
Stocks lie above SML2m
Calculate Jensen's Alpha2m
- Fama-French Three- Factor ModelUnderstand the Fama-French three-factor model. Calculate expected returns using the Fama-French Three-Factor Model.Fama-French Three-Factor Model3m 29s
Factors of the Fama-French Model2m
Size Factor Exposure2m
High Book to Market Ratio Stock2m
Calculation of SMB and HML Factor10m
SMB Calculation2m
HML Calculation2m
Expected Returns using Fama-French Model10m
Calculate Beta of Fama-French Factors5m
- Fama-French Five-Factor ModelUnderstand the Fama-French Five-Factor Model and its factors.Fama-French Five-Factor Model10m
Profitability Factor2m
Investment Factor2m
Test on Beta, CAPM, and Fama-French12m
- Factor InvestingUnderstand factor investing and different types of factors. How different factors work and their application in trading.Factor Investing2m 36s
Macroeconomic Factors2m
Good Factors2m
Applications of Factor Investing3m 4s
Choose Factor Strategy2m
Benefits of Factor Investing2m
Which Factor Works Best?2m
- Multi Factor ModelUnderstand momentum and short-term reversal factors. Create multiple factors and then combine them to form a multi-factor portfolio.
Multi-Factor Model: Momentum Factor2m 25s
Stock Selection in Factor Model2m
Selection Criterion2m
Benefits of Negative Correlation2m
Assumption of Momentum Factor2m
Timeframe of a Factor2m
Interpretation of Momentum Factor2m
Multi-Factor Model: Reversal Factor2m 33s
Short-Term Reversal Factor2m
Determination of Existing Trend2m
Interpretation of Short-Term Reversal Factor2m
The Momentum Factor in Python10m
Create the Momentum Factor5m
Stocks to Buy/Sell using Momentum Factor5m
Paper/Live Trading Momentum Factor Strategy10m
The Short-Term Reversal Factor in Python10m
Create the Short-Term Reversal Factor5m
Stocks to Buy/Sell using Short-Term Factor5m
Combine the Factors5m
Paper/Live Trading Multi-Factor Strategy10m
Test on Factors and Multi-Factor Investing10m
- Portfolio Performance AnalysisLearn to analyze the portfolio using multiple performance measures such as Sharpe ratio, maximum drawdowns, Sortino ratio and many more metrics. Python code is provided to calculate all these performance metrics with an example.Portfolio Performance Analysis10m
Calculate Sharpe Ratio in Python5m
Calculate Sortino Ratio in Python5m
Calculate Skewness in Python5m
Annualised Volatility2m
Calculate the Sortino Ratio2m
Calculate the Information Ratio2m
Calculate the Maximum Drawdown2m
Test on Performance Analysis and Paper Trading.10m
- 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
- Capstone ProjectIn this section, you will undertake a capstone project on real-world data. This project will require you to apply and practice the concepts learnt throughout this course.Capstone Project: Getting Started10m
Problem Statement10m
Frequently Asked Questions10m
Template Code Files2m
Model Solution: QPM Capstone Project10m
Capstone Solution Downloadable2m
- SummaryThis section includes a downloadable zipped folder with all the codes and notebooks for easy access.Summary1m 35s
Python Codes and Data2m
Position Sizing in Trading
- IntroductionPosition sizing is not a magical wand which can make any strategy profitable. In this section, you will understand the course structure, and the various teaching tools used to make your learning experience smooth and untroubled. These tools include videos, quizzes, strategy codes and capstone projects. The interactive methods used help you to not only understand the concepts, but also how to implement the strategies in the live markets.
Course Introduction5m 7s
Course Structure3m 41s
Course Structure Flow Diagram10m
Getting Started With Quantra4m 9s
- What is Position Sizing and Money Management?It is always amazing to hear about stalwarts putting all their money on one asset and winning big. Unfortunately, these are more exceptions than the norm. A rational trader would always diversify and allocate capital to different trades. Position sizing techniques have been developed to help the trader allocate their capital efficiently. In this section, you will be introduced to the concept of position sizing and what it can and cannot do.
Importance of Position Sizing and Money Management1m 50s
Primary Purpose of Money Management2m
Ideal Allocated Capital2m
Drawback of Absolute Fixed Allocation2m
Allocation of Capital2m
Use of Money Management2m 38s
Objective of Successful Money Management2m
Properties of Coin Toss Game2m
Ideal Bet Size2m
Transformation of Profitable to Unprofitable Strategy2m
- Position Sizing TermsBefore moving to position sizing techniques, it is crucial to understand the position sizing performance measures. In this section, you will learn about the common position sizing measures such as trading system expectancy, win/loss ratio and trade size. Along with these, you will also learn about the most common measures used in risk management, such as volatility and maximum drawdown.
Performance Measure Terms3m 41s
Trade Size2m
Win/Loss Ratio2m
Trading System Expectancy2m
Percentage of Winning Trades2m
Trading Systems2m
Leverage10m
Broker and Asset Leverage2m
Total Leverage Calculation2m
Risk Management Terms1m 15s
Volatility2m
Volatile Strategy2m
Maximum Drawdown2m
Calculate Maximum Drawdown2m
Using Jupyter Notebook1m 54s
Calculate Volatility & Drawdown in Python10m
Calculate Volatility5m
Calculate Drawdown5m
- Trading StrategyTo apply the position sizing techniques, you need to have a trading strategy. In this section, you will learn about the pillars of the index-reversal strategy. The trading rules of the index-reversal strategy are also covered in this section.Index Reversal Strategy5m 13s
Popularity of Indices2m
The Behaviour of Asset Price2m
Pillars of the Index Reversal Strategy2m
Short-term Reversal Strategy2m
Strategy Implementation3m 8s
Overnight Returns vs Intraday Returns2m
Capturing the Overnight Returns2m
Price Jump After Local Minimum Price2m
Index Reversal Strategy Trading Rules2m
Local Minimum Day2m
Market Exposure in Index Reversal Strategy2m
Determining Strategy Entry Signal2m
Trading Instruments10m
Additional Reading for Trading Strategy10m
- Implementation of the Trading StrategyIn this section, you will learn to apply the index-reversal strategy in a Jupyter notebook. The strategy performance metrics are also calculated and a utility function is created to make the analysis of other strategy returns easier.Index Reversal Strategy Implementation10m
Trading Signals5m
Cumulative Strategy Returns5m
Portfolio Value5m
Annualised Returns5m
- Basic Position Sizing: Fixed Units and Fixed SumThis section will introduce you to one of the two most common position sizing techniques which are fixed units and fixed sum. You will learn about the intuition behind fixed units and fixed sum methods with their pros and cons. Along with the concept, you will also learn to apply both methods on the index reversal strategy and analyse how these position sizing methods affect the strategy performance.Fixed Units and Fixed Sum4m 14s
Number of Units2m
Overall Weight2m
Disadvantages of Fixed Units Method2m
Number of Units Using Fixed Sum Method2m
Advantages of Fixed Sum Method2m
Implementation: Fixed Units2m 18s
Number of Units in the Fixed Units2m
Leverage in Fixed Units2m
Fixed Units Implementation10m
Fixed Units5m
Implementation: Fixed Sum1m 22s
Fixed Sum Leverage and Portion of Capital2m
Number of Units in Fixed Sum2m
Fixed Sum Implementation10m
Fixed Sum5m
- Basic Position Sizing: Fixed Percentage and Fixed FractionFixed percent and fixed fraction are position sizing techniques, where you spend only a fixed portion of the available capital to place trades. Both these methods will be introduced in the section with the implementation of the fixed percentage method on the index reversal strategy.Fixed Percentage and Fixed Fraction2m 27s
Number of Units Using Fixed Percentage2m
Effect on Trading Size2m
Number of Units Using Fixed Fraction2m
Implementation: Fixed Percentage46s
Returns and Drawdown in Fixed Percentage2m
Leverage in Fixed Percentage2m
Portion of Capital in Fixed Percentage2m
Fixed Percentage Implementation10m
Fixed Percentage5m
- Volatility TargetingVolatility targeting is an advanced position sizing technique. As the volatility of the underlying goes up, the trade size is scaled down. In this section, you will learn about different volatility models and how to calculate volatility using them.
Introduction to Volatility Targeting3m 54s
Level of Volatility2m
Effect of Volatility Targeting2m
Volatility of Volatility Targeted Portfolio2m
Leverage for Volatility Targeted Portfolio2m
Performance of Volatility Targeted Portfolio2m
Sharpe Ratio for Volatility Targeted Portfolios2m
Different Volatility Models2m 59s
Volatility Estimation2m
Average True Range2m
Equal Weighted Returns2m
Exponentially Weighted Returns2m
Volatility Clustering2m
GARCH Model2m
Volatility Models10m
Calculate EWMA Volatility5m
Interpretation of ATR Plot2m
- Application of Volatility TargetingIn this section, you will learn to apply the volatility targeting technique on the index reversal strategy. The performance metrics, leverage ratio, and the portion of capital used by this position sizing technique, are calculated in a Jupyter notebook.Application of Volatility Targeting3m 38s
Application of Volatility Targeting10m
Leverage Based on Volatility Target5m
Returns Based on the Leverage5m
Risk Exposure in Volatility Targeting2m
Portion of Capital in Volatility Targeting2m
- 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 TemplateThis section talks about the implementation of the position sizing technique on Blueshift from which you can paper trade and/or live trade.Section Overview10m
Paper/Live Trading Volatility Targeting Method10m
FAQs for Live Trading on Blueshift10m
- Constant Proportion Portfolio InsuranceConstant Proportion Portfolio Insurance is another advanced position sizing technique that protects the downside. It guarantees a minimum return at the end of a period. This section will introduce you to this technique. You will also learn how to implement this in Python and then apply the technique on the index reversal strategy.Introduction to Constant Proportion Portfolio Insurance2m 34s
Protection Level2m
Scale of Exposure in CPPI2m
Portfolio Value Minus Floor2m
Risky Asset Allocation2m
Advantages and Disadvantages of CPPI2m 8s
Disadvantages of CPPI2m
Gap Risk2m
Reason for Gap Risk2m
Multiplier2m
Exposure to Risky Assets2m
Risk to Lose2m
Value of the Multiplier2m
Allocation to SPY ETF2m
Decrease in Portfolio Value2m
Allocation to Riskfree Asset2m
Application of CPPI5m 14s
CPPI Implementation2m
Leverage in CPPI2m
Implementation of CPPI10m
Paper/Live Trading CPPI Method10m
- Time Invariant Portfolio ProtectionCPPI guarantees a minimum return at the end of a period, but fails to capture the portfolio highs. In this section, you will learn how to overcome this by adjusting the floor based on the peak value of the portfolio. You will do this by applying the technique on the index reversal strategy.Implementing Time Invariant Portfolio Protection10m
Limitations of CPPI2m
Floor in TIPP2m
Additional Reading10m
Paper/Live Trading TIPP Method10m
- Kelly FormulaIn this section, you will learn about the Kelly formula and how to use it. Kelly formula is a technique used to calculate the trade size that ensures the maximum return without focusing on the risk of return. You will also learn how to implement this in Python. You will further learn the limitations of this technique.Kelly Formula4m 8s
Objective of Kelly Formula2m
Decisions to Open a Position2m
Trade Size2m
Win/Loss Ratio2m
Kelly Percentage2m
Implementation of Kelly Criterion10m
Calculate Winning Probability and Win/Loss Ratio5m
Calculate Kelly Percentage5m
Limitations of Kelly Formula1m 55s
Kelly Formula in Trading2m
Disadvantages of Kelly Formula in Trading2m
Additional Reading10m
- Optimal FThe major disadvantage of the Kelly formula is that it is applicable only on binary outcomes, and thus is not directly usable in trading. This is overcome by optimal f. In this section, you will learn about this technique and its implementation in Python. You will also apply this technique on the index reversal strategy.Optimal F1m 39s
Features of Optimal F2m
Range of Optimal F2m
Value of Optimal F2m
Implementation of Optimal F10m
Additional Reading10m
Paper/Live Trading Optimal F Method10m
- Theory Is Grey, but Life Is GreenPosition sizing techniques can work on a trading strategy exceptionally well and yet falter in the real world. Sometimes, the position sizing techniques, such as Kelly fraction or optimal f, have their own limitations. Other times, the financial markets themselves pose unique challenges to these techniques. In this section, you will look at these challenges and learn how to overcome them.Inherent Risk in Kelly Criterion and Optimal F4m 1s
Properties of Kelly Criterion Criterion and Optimal F2m
Probability of Drawdown2m
Reduction in Probability of Drawdown2m
Optimal and Real Bet Size2m
Relation Between Probability and Drawdown2m
Fractional Kelly and Probability of Drawdown2m
Fractional Kelly and Profit Potential2m
Relation Between Fractional Kelly and Expected Profit2m
Optimal Kelly Fraction2m
Hidden Risks in Backtesting and Financial Markets4m 21s
Out and In Sample Returns2m
Compensation of Out of Sample Returns2m
Stationarity of Price Series2m
Impact of Non-Stationarity2m
Significance of Fat Tails2m
Black Swan Events2m
Focus of Position Sizing2m
Dealing with Unprofitable Trading Strategy1m 44s
Turning Off Trading Strategy2m
Advantage of Multi Strategy Portfolio2m
Capital Allocation Based on Performance2m
Correlation in Multi-strategy portfolio2m
Martingale Trading Strategy3m 41s
Use of Martingale Trading Strategy2m
Additional Reading10m
- Numerical MethodsHave you ever wondered what would have happened if the past was different? How a trading strategy would perform differently due to some unexpected events in the past. In this section, you will explore alternative trading realities and learn from them. This section will introduce bootstrapping and Monte Carlo methods, which helps you get deeper insights into a trading strategy by exploring multiple scenarios. You will also learn to do bootstrapping simulations on the index reversal strategy and gain more insights.Bootstrapping3m 3s
Need of Bootstrapping2m
Bootstrapping Process2m
Inference from Bootstrapping Data-I2m
Inference from Bootstrapping Data-II2m
Estimate Parameters2m
Bootstrapping Results1m 48s
Bootstrap Simulation10m
Maximal Drawdown Distributions2m
Bootstrapping Result Interpretation2m
Capital Allocation Based on Bootstrapping Results2m
Monte Carlo2m 33s
How Much Capital Allocated?2m
Monte Carlo Method2m
Monte Carlo Process2m
Advantages and Disadvantages of Monte Carlo2m
- Conservative Framework for Position SizingOnce you have gained the knowledge and have applied the position sizing techniques on a trading strategy, you will take the next big step, combining two position sizing techniques! Not only that, you will analyse the trading strategy’s performance as well.Testing the Trading Strategy2m 58s
Reason for Position Sizing2m
Maximisation of Returns through Position Sizing2m
Risk and Position Sizing2m
Limitations of Backtesting2m
Leverage Boundaries2m
Long Historical Data2m
Conservative Estimate of Leverage2m
Revisiting CPPI and Volatility Targeting3m 19s
CPPI and Drawdown2m
CPPI Based Allocation2m
Result of CPPI and Volatility Targeting2m 9s
Analysing CPPI and Volatility Targeting Performance2m
Implication of Dynamic Position Sizing2m
Impact of High Risk Budget and High Leverage2m
Position Sizing and Unprofitable Trading Strategy2m
Implementing TIPP with Volatility Targeting10m
Paper/Live Trading TIPP with Volatility Targeting10m
- Automate Trading Strategy Using IBridgePyAdditional Reading10m
Sample Strategies to Run on Interactive Brokers2m
- 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
Installing Ta-Lib2m
Quantra Environment2m
Troubleshooting Tips For Setting Environment10m
How to Run Files in Download Section?10m
Troubleshooting For Running Files in Download Section10m
- Capstone ProjectIn this section, you will undertake a capstone project where you will apply different position sizing techniques to a trading strategy. The performance of the two sizing techniques is compared. This project helps you to practice and apply the concepts learnt in this course.Capstone Project: Getting Started10m
Problem Statement10m
Frequently Asked Questions10m
Code Template and Data Files2m
Model Solution: Position Sizing Capstone Project10m
Capstone Solution Downloadable2m
- 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 25s
Python Data and Codes2m
Factor Investing: Concepts and Strategies
- IntroductionAn approach to investing that focuses on specific drivers of return across asset classes is factor investing. This section serves as a preview to 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 about factor investing. 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 projects.
- Understanding Smart BetaAfter completing this section you will be able to define Alpha and Beta. You will also be able to explain the concept of Smart Beta and its advantages over traditional index investing and active investing.
Understanding Alpha and Beta3m 1s
Define Alpha5m
Identify Alpha5m
Negative Alpha5m
Define Beta5m
Indication of Beta5m
Beta between 0 and 15m
Smart Beta2m
Traditional Index Investing5m
Active Investing and Index Investing5m
Smart Beta and Active Investing5m
Describe Smart Beta5m
Smart Beta Advantages5m
Research Aspect of Smart Beta5m
Additional Reading on Smart Beta2m
- All About FactorsIn this section, you will learn about what factors are and how they influence the price of a security. Discover how factors lead to rewards and how the factor approach helps extract these rewards. In addition to this, you will also learn about all the ways that factor investing can be the right choice for you.Factor Premiums2m
Define Factors5m
Reason for Factor Premium Existence5m
Uses of factors5m
Post Earnings Announcement Drift5m
Earnings Announcement5m
Factors and Asset Performance5m
Define Factor Premiums5m
Factor Based Trading5m
Factor Based Advantages2m
Basis for Factor Approach5m
Persistence in Factors5m
Factors and Trading Rules5m
Cost of Factor-Based Approach5m
Rule-Based Approach5m
Long-Term Persistence5m
Existence of Factors5m
Factors and Risk5m
Additional Reading on Factor Investing2m
- Fundamental and Price DataAny strategy hypothesis requires data on which you can backtest and analyse the strategy performance. In this section, you will be able to retrieve the fundamental and price data of the top 100 U.S. stocks and build your stock universe which will be used later to create various factor-based strategies.Uninterrupted Learning Journey with Quantra2m
Fetching Fundamental Data5m
Creating Stock Universe5m
Market Capitalisation5m
Fill the Missing Values5m
- Factor ApproachIn this section, you will go through the different types of factors which have been used by different investors and traders and also look at a few popular factors.Brief History of Factors2m
Identification of Factors by Fama French5m
Initial Factors of Fama French Model5m
Discovery of New Factors5m
Types of Factors2m
Classification of GDP5m
Popular Style Factors5m
- What is Value?In this section, you will understand the core of the value factor and how it can be useful in your portfolio.What is Value?2m
Factor and Low Price5m
Common Denominator Between New and Present Companies5m
Meaning of Value for Money5m
Perception of Value5m
Stock Selection5m
- Quantifying ValueYou have heard of the phrase, “value for money stock”. Or “the stock is undervalued”. In this section, you will try to identify the right fundamental ratio which can be used to objectively pick an undervalued stock from a given stock universe.Quantifying Value2m
Points of Consideration While Quantifying Value5m
Application of Earnings Per Share5m
Calculation of P/E Ratio5m
Low Value of P/E Ratio5m
Importance of Financial Ratios5m
Importance of P/E Ratio5m
Comparison of Stocks Based on P/E Ratio5m
Financial Ratios2m
Calculation of Financial Ratios5m
- Identification of Undervalued StocksOnce you have identified the right metrics to identify an undervalued stock, you will begin the process of creating a value-based strategy by first identifying the top 10 undervalued stocks from our stock universe.
Creation of Value Strategy2m
Objective of Value Strategy5m
Identification of Undervalued Stocks Using PE Ratio5m
Using Two Ratios for Identification of Value5m
Top Undervalued Stocks5m
Combination of Financial Ratios5m
PE Ratio and Value of a Stock5m
PB Ratio and Value of Stock5m
Average Rank and Value of Stock5m
Stock Choice Based on Rank5m
Strategy Flow Diagram2m
Identification of Undervalued Assets Using Financial Ratios5m
Check Start of Month of a DataFrame5m
Select First Day of Month5m
Rank Stocks in Ascending Order5m
- Performance Analysis of Value Based StrategyIn this section, you will generate signals to go long on the top 10 undervalued stocks from our stock universe and analyse the performance of the value factor based strategy.Generation of Signals for Value Strategy5m
Rebalancing Portfolio5m
Performance Analysis of Value Strategy5m
CAGR5m
Sharpe Ratio5m
Summary2m
- Introduction to Absolute Valuation MethodIn the earlier sections, you focussed on relative valuation, where you compare different stocks based on a common metric. In this section, you will focus on the intrinsic value of a stock and assess if the stock is a good buy or not.What is Absolute Valuation2m
Definition of Value5m
Purpose of Absolute Valuation5m
Valuation Method5m
How Does Absolute Valuation Work2m
Essence of Valuation5m
Formula of Absolute Valuation5m
Addition to Absolute Valuation Formula5m
Rate of Return and Valuation Formula5m
Caution of Absolute Valuation Formula5m
Standardisation of Growth Rate5m
Drawback of Absolute Valuation Formula5m
- Different Approach to ValueThe value based approach has been in existence for decades. But lately, a new approach to valuation has become popular, where you try to forecast the present value of the future earnings of a stock. You will understand the intuition behind this approach in this section. Further, you will also bust some myths around value factor based investing.Intuition of DCF Valuation Method2m
Definition of Cash Flow5m
Steps in DCF Valuation Method5m
Calculation of Present Value5m
Terminal Value and DCF Valuation5m
DCF Value Per Share5m
Usage of Discount Rate in DCF Valuation5m
Difference in Value Using DCF Valuation5m
Limitation of DCF Valuation5m
Calculation of Present Value of Next Five Years5m
Choice of Asset Based on DCF5m
Six Common Myths Of Value Investing3m 28s
Value Investing Related Myths5m
Application of Value Investing Principles5m
Challenges of Value Investing5m
Additional Reading2m
- Capstone Project - IIn this section, you will use the learnings from the value based strategy to create a unique strategy on your own.Getting Started2m
Problem Statement2m
Capstone Project - I Solution2m
- Momentum FactorIn 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 Exists2m
Primary Assumption of Momentum5m
Herding Effect Definition2m
Herding Effect Towards Amazon2m
Reason for PEAD Effect2m
Momentum in Futures2m
Reasons for Momentum2m
Effect of Client Redemptions2m
Index Tracker Fund Performance2m
Trading Momentum5m
Characteristics of Momentum2m
Main Challenge with Persistence of Trends5m
Avoiding Loss Due to Trend Reversal5m
Define a Momentum Crash5m
Dealing with Momentum Crashes5m
Strength in Momentum5m
Strong Momentum5m
Holding Period5m
Additional Reading on Momentum Factor2m
- Time Series MomentumThe 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 and analyse the performance of this strategy.
Types of Momentum2m
Identifying Winners2m
Winner and Loser Ratio2m
Time Series Momentum2m
Lookback and Holding Period2m
Trading Decision Based on Returns2m
Essential Points for Momentum Trading2m
Reason for Underperformance of Strategy2m
Strategy Flow Diagram: Time Series Momentum2m
Time Series Momentum Strategy5m
Calculate Returns5m
Generate TSMOM Signals5m
Strategy Flow Diagram: TSMOM with Volatility Adjusted Returns2m
TSMOM with Volatility Adjusted Returns5m
Calculate Volatility Adjusted Returns5m
Align Signal Index with Rebalanced Index5m
Additional Reading on Time Series Momentum2m
- Live Trading on BlueshiftLearn 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.Section Overview2m 19s
Live Trading Overview2m 40s
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 live trading strategy template. You can tweak the code by changing securities or the strategy parameters. You can also analyse the strategy's performance in more detail.FAQs for Live Trading on Blueshift5m
Paper/Live Trading TSMOM Strategy2m
- Cross Sectional MomentumThe 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 cross sectional momentum strategy on S&P500 stocks and analyse the strategy's performance.Cross Sectional Momentum2m
Types of Momentum2m
Momentum in Returns2m
Which Lookback and Holding Period?2m
Factor to Filter Stocks?2m
Steps for Cross Sectional Momentum Strategy2m
Which Fund House?2m
Impact of High Number of Stocks2m
Lookback and Holding Period2m
Strategy Flow Diagram: CSMOM2m
Cross Sectional Momentum Strategy10m
Calculate Average Dollar Volume5m
Rank the Filtered Stocks5m
Generate Buy Signals5m
Compute Trading Cost5m
Calculate Lookback Returns With Skip Days5m
Momentum Recap2m
- Value and MomentumRelying on momentum in all phases of the market may not be the right call. To create a well-rounded portfolio, you can try to blend other factors like value. This section explains how blending value and momentum factors can be the right fit for each other. After completing this section, you will be able to create an equally weighted portfolio consisting of two factors, i.e. value and momentum.
Combining Value and Momentum2m
Ways to Combine Value and Momentum5m
The Upside of Combining Value and Momentum5m
Filtering Stocks5m
Combining Value and Momentum Factor5m
Merging Dataframes5m
Create an Equally Weighted Portfolio5m
Additional Reading on Value and Momentum2m
Test on Value and Momentum Factors16m
- Size FactorIn this section, you will learn the reasons for the out-performance of small-cap companies and how to capture this outperformance.Size Factor: Definition and Intuition3m 48s
Definition of Size Factor5m
Outperformance of Small-Caps5m
Lack of Attention5m
Trading in Small-Cap Stocks5m
Emma’s Dilemma5m
Characteristics of Size Factor2m
Capturing the Size Factor5m
- Introduction to Quality FactorThe quality factor is quite popular among legendary investors like Warren Buffett, but is also the most confusing. In this section, you will unravel the basic tenets of selecting a quality stock.Part Overview2m
Prerequisite for Quality Factor2m
Factors Apart from Quality5m
Importance of Financial Statements Analysis5m
Financial Statements and Corporate Governance5m
Corporate Governance Checks2m
Hidden Losses5m
Artificial Increase in Profitability5m
Identification of Suspicious Activities5m
Need of Independent Auditors5m
Challenges in Identification of Fraudulent Companies5m
Significance of Reporting Expenses as Investments5m
- Creation of Quality StrategyIn this section, you will apply the principles of the quality factor to identify and go long on quality stocks.How to Identify Quality Stocks2m
Common Elements of Quality Stocks5m
Measurement of Company's Ability to Navigate Business Cycles5m
Evaluation of Growth in Quality Stocks5m
Identifying Quality Stock Based on Growth5m
Combination of Metrics for Quality Factor5m
Difficulty of Identifying Quality Stocks5m
Identification of Profitability Element5m
Strategy Flow Diagram of Quality Strategy2m
Creation of Quality Strategy5m
Additional Reading2m
- Factor TimingDifferent factors perform differently across market phases and durations. This section discusses whether you can improve the performance of your strategy by considering the timing of individual factors and taking positions accordingly. It also uncovers some of the challenges you may face while adapting to this approach.Factor Timing2m
Define Factor Timing5m
Factor Timing Approach5m
Types of Factor Timing5m
Timing the Entry and Exit5m
Strategy Flow Diagram: Factor Timing2m
Factor Timing with RSI5m
Calculate RSI5m
RSI Strategy5m
Drawbacks of Factor Timing2m
Challenges of Factor Timing5m
Incorrectly Timing Factors5m
Higher Trading Frequency5m
Complexity of Factor Timing5m
Multi-Factor Approach5m
Additional Reading on Factor Timing2m
FAQs on Factor Timing2m
- Identifying Relevant FactorsThis section covers the need to identify relevant factors to create a multi-factor portfolio. This section also covers the methods to screen the factors such as correlation analysis, robustness checks and performance filters.Need to Identify Relevant Factors2m
Relevant Factors5m
Aim of Selecting Relevant Factors5m
Factor Screening Methods5m 22s
Purpose of Factor Screening5m
Purpose of Correlation Analysis5m
Purpose of Robustness Check5m
Factor Screening with Correlation Analysis5m
Screen Factors with Correlation Analysis5m
Threshold for Correlation Analysis5m
Performance Filter and Robustness Check5m
Screen Factors with Performance Filter5m
Screen Factors with Robustness Check5m
FAQs2m
Additional Reading for Identifying Relevant Factors2m
Section Recap2m
- Capital Allocation To FactorsIn this section, you will learn to allocate capital to multiple factors. you will learn the drawbacks of using equal weightage method for capital allocation and explore ranking method for capital allocation.How to Allocate Capital to Different Factors?2m
Equal-Weightage Approach5m
Drawback of the Equal-Weightage5m
Historical Metrics for Capital Allocation5m
Ranking Method Based on Sharpe Ratios5m
Capital Allocation Using the Ranking Method5m
Assign Ranks Based on Sharpe Ratio5m
Assumption of Ranking Method5m
Ranking Method With Single Historical Metric5m
Rank the Factors Based on the Sharpe Ratio5m
Section Recap2m
FAQ on Capital Allocation To Factors2m
- Ranking Method With Multiple MetricsIn this section, you will learn to calculate capital allocation for factors based on multiple historical metrics using the ranking method.Apply Ranking Method With Multiple Metrics2m
Ranking The Factors With Higher Volatility5m
Formula to Calculate the Capital Allocation5m
Ranking Factors Using the Ranking Method5m
Purpose of Assigning Ranks5m
Ranking Based on the Sharpe Ratio5m
Efficient Method to Calculate Capital Allocation5m
Purpose of Average Rank5m
Inverting the Ranking Logic5m
Capital Allocation With Ranking Method5m
Calculate the Historical Metrics5m
Rank the Cumulative Returns5m
Code to Rank Based on Volatility5m
Drawback of Ranking Method2m
Main Drawback of Ranking Method5m
Overcome the Drawback of the Ranking Method5m
Section Recap2m
FAQ on Ranking Method With Multiple Metrics2m
- Scoring Method for Capital AllocationIn this section, you will learn the scoring method for capital allocation and implementation of the same in Python. You will also learn how the scoring method overcomes the drawback of the ranking method.Scoring Method for Capital Allocation2m
Scoring Sharpe Ratio and Cumulative Returns5m
Range of Historical Metric in Scoring Method5m
Using Volatility for Capital Allocation5m
Min-Max Scaling Formula5m
Calculation of Capital Allocation for Factors5m
Volatility Inversion in Scoring Method5m
Benefits of Min-Max Scaling5m
Capital Allocation With Scoring Method5m
Scale the Factors Using the Minmax Scaler5m
Formula of Capital Allocation With Scoring5m
FAQs on Scoring Method for Capital Allocation2m
Additional Reading for Capital Allocation To Factors2m
Section Recap2m
- Compare the Capital Allocation MethodsIn this section, you will learn the comparison between the capital allocation methods, ranking and scoring.Compare The Ranking and Scoring Methods2m 37s
Primary Drawback of the Ranking Method5m
Calculate Scores for Factors5m
Scaled Historical Metrics for Capital Allocation5m
Determine Capital Allocation by Scoring Method5m
- Backtesting The Factor CombinationIn this section, you will learn to combine the factors to create a portfolio based on the screening and capital allocation techniques learned so far. In addition to this, you will also learn to rebalance the portfolio at regular intervals and study its performance.Strategy Flow Diagram2m
Backtest Multi-Factor Portfolio Part-15m
List to Store the Rebalancing Days5m
Study the Performance in Each Rebalance Cycle5m
Backtest Multi-Factor Portfolio Part-25m
Backtest the Multi-Factor Portfolio5m
Performance of the Multi-Factor Portfolio5m
FAQs on Backtesting The Factor Combination2m
Assessment Test14m
- Exploring Unknown FactorsDelve into uncharted territories by embarking on an exploration of unknown factors. Navigate through unexplored dimensions to uncover hidden insights and expand the boundaries of knowledge.Exploring Unknown Factors2m
Existence of Unknown Factors5m
Machine Learning Models5m
Sentiment Analysis5m
Technical Analysis5m
Research Papers5m
Personal Trading Experience5m
- Capstone Project - IIIn this section, you will use the learnings from the factor combination based strategy to create a unique strategy on your own.Getting Started2m
Problem Statement2m
Capstone Project - II Solution2m
- Live Trading on IBridgePyIn 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 Overview2m 2s
Live Trading Overview2m 41s
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 TradingTo 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 Documentation10m
Template Code File2m
- Run Codes Locally on Your MachineIn 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 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
- SummaryIn this section, we will summarise all the concepts taught in the course. This section also consists of all the data and code files used in the course.Course Summary2m
Summary and Next Steps2m
Python Codes and Data2m
Quant Investing for Portfolio Managers
- Introduction to the CourseThis 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.
- Fundamentals of Factor InvestingThis section tackles the first question which arises in every portfolio manager's mind, "Why should I create a portfolio using factors?" You will also explore the journey of factor investing, right from the CAPM to the newer models introduced in the 21st century.
Why Factor Investing?2m
Define Factor Investing5m
Factor Investing vs Actively Managed Funds5m
Multi-Factor Portfolio5m
Performance of Factor Based Portfolios5m
Journey of Factor Investing2m
CAPM and Influence on Returns5m
Three-Factor Model5m
Five-Factor Model5m
Define Factor Premium5m
Traditional Factor5m
Purpose of Identifying Factors5m
Types of Factors2m
Core Building Blocks of Factor Investing5m
Identify Non-Traditional Factor5m
Characteristics of Non-Traditional Factors5m
Additional Reading on Fundamentals of Factor Investing2m
Test on Fundamentals of Factors12m
- Why Traditional Factors Work?Traditional Factors have been around since decades, and yet they are still in practice among leading fund houses. Take a deep dive into the world of traditional factors and understand how they work. You will also get a brief overview on how you can create a traditional factor portfolio.Why Traditional Factors Work?2m
Identification of Style Factors5m
Stock Classification According to Quality5m
Reason of Momentum Factor5m
Focus of Value Factor5m
Size Factor Interpretation5m
Institutional Investors and Small-Cap Stocks5m
Belief in Value Investing5m
Analysis Based on Quality Factor5m
Analysis Based on Value Factor5m
Analysis Based on Size Factor5m
- Traditional Factor Investing and PerformanceThe popularity of traditional factors has made portfolio managers around the world to sit up and take notice. There are a number of thematic ETFs which are developed by institutions to cater to the retail trader. You can explore their performance in this section.Investing in Factors and Factor Based Fund Performance2m
Approaches to Factor Investing5m
Creation of Portfolio Using Value Factor5m
Limitation of P/E Ratio Based Value Investing5m
Flexibility of Factor Investing5m
Investing in Multiple Factors5m
FAQs on Traditional Factors2m
Summary of Traditional Factors2m
Additional Reading of Traditional Factors2m
Test on Traditional Factors12m
- Existence of Non-Traditional FactorsTraditional Factors are not the only factors in existence. Both academicians and professional traders are exploring the world of finance to uncover hidden sources of alphas, which are being called non-traditional factors. In this section, you will also understand how non-traditional factors can be discovered.
Why Do Non-Traditional Factors Exist?2m
Reason for Popularity of Non-Traditional Factors5m
Traditional Factors and Alpha5m
Example of Non-Traditional Factor5m
Non-Traditional Factors and Portfolio Performance5m
Difference Between Non-Traditional and Traditional Factors5m
How to Find Non-Traditional Factors?2m
Identification of Non-Traditional Factors5m
Example of Alternative Data for Identification of Factors5m
Skewness as Non-Traditional Factor5m
Action After Identification of Non-Traditional Factor5m
Research Papers and Non-Traditional Factors5m
FAQs on Non-Traditional Factors2m
Summary of Non-Traditional Factors2m
Additional Reading of Non-Traditional Factors2m
- Getting Data: Multiple AssetsIn this optional section, you will explore how to retrieve price data of multiple assets which can be used to create a factor portfolio.Uninterrupted Learning Journey with Quantra2m
Getting Data: Multiple Assets5m
- How to Calculate Skewness?In this optional section, you will recall the meaning of skewness and how it can be calculated from a dataset.How to Calculate Skewness?1m 39s
Skewness Measure5m
Indication of Positive Skew5m
Skewness and Normal Distribution5m
- Creation of Non-Traditional Factors PortfolioIn this section, you will focus on the skewness factor which can be used to create and rebalance a non-traditional factor based portfolio.Creation of Skewness Factor Based Portfolio2m
Relation Between Past Skewness and Future Returns5m
Data Frequency to Calculate Skewness5m
Type of Stocks Excluded in Portfolio Creation5m
Average Weekly Returns5m
Modification to Strategy in Research Paper5m
Restriction of Potential Stock Universe5m
Strategy Flow Diagram for Skewness Strategy2m
Creation of Non-Traditional Factor Based Portfolio5m
Calculate Skewness of Weekly Returns5m
Calculate Absolute Value of Skewness5m
Select 10 Assets with Lowest Skewness5m
- Challenges in Creation of Non-Traditional Factor PortfolioIn this section, you will list the reasons it is difficult to create a non-traditional factor portfolio.Challenges in Creation of Non-Traditional Factor Portfolio2m
Primary Challenge of Acquiring Data for Non-Traditional Factors5m
Sentiment Analysis and Bias5m
Method to Compare Non-Traditional Factor Data Across Assets5m
Traditional and Non-Traditional Factor Portfolio5m
FAQs on Creation of Non-Traditional Factors Portfolio2m
Summary of Creation of Non-Traditional Factors Portfolio2m
Additional Reading of Creation of Non-Traditional Factors Portfolio2m
Test on Creation of Non-Traditional Factors Portfolio10m
- Capstone Project on Non-Traditional Factor PortfolioIn this capstone project section, you will create a portfolio based on the kurtosis factor.Getting Started2m
Problem Statement2m
Capstone Project Model Solution2m
- Factor TimingExplore how market dynamics influence factor performance, the concept of factor timing, and practical approaches like economic cycle forecasting and price-based momentum for better portfolio management.
Factor Timing: Why and How?2m
Factor Outperformance5m
Purpose of Factor Timing5m
Timing is Money5m
Economic Cycles for Factor Timing5m
Momentum Approach5m
FAQs on Factor Timing2m
Additional Reading on Factor Timing2m
- Generalized Hurst ExponentUnderstand the Generalized Hurst Exponent as a tool to analyse market trends, identify momentum, and refine factor timing strategies.Generalized Hurst Exponent2m
GHE - Time Series5m
Time Series Behaviour5m
Interpretation of GHE5m
Variation with q5m
Estimating GHE5m
Generalized Hurst Exponent Calculation5m
Calculate the Logarithm of Lag Values5m
Perform a Linear Regression to Fit Log-Lags to Log-Moments5m
Calculate the Generalized Hurst Exponent5m
FAQs on Generalized Hurst Exponent2m
Additional Reading on Generalized Hurst Exponent2m
- Getting ETF DataDesigning and creating custom factors from data demands expertise, time, and resources. An alternative approach is to invest in ETFs that provide targeted exposure to specific factors. In this section, you will learn how to identify relevant ETF tickers, filter them according to your investment strategy, and retrieve their price data.How to Find ETF Data?2m
Selecting ETFs and Fetching Data15m
- Factor Timing StrategyLearn to develop factor timing strategy by combining the Generalized Hurst Exponent to detect trends and technical indicators like Momentum (MOM) for confirming positive momentum signals.Factor Timing Strategy2m
Purpose of Hurst Exponent5m
Trending Market5m
MOM Threshold5m
Long-Only Strategy5m
Lower MOM Threshold5m
Factor Timing Strategy Flow Diagram2m
Factor Timing Single ETF5m
Calculate the Momentum (MOM) Indicator5m
Trading Signal5m
Factor Timing Portfolio ETFs5m
Calculate the Benchmark Returns5m
Calculate the Portfolio Returns5m
FAQs on Factor Timing Strategy2m
Additional Reading on Factor Timing Strategy2m
- Effectiveness of Factor TimingExamine the strengths and limitations of factor timing strategies, including insights from recent research, and explore how timing can reduce drawdowns, align with economic conditions, and improve portfolio resilience.Effectiveness of Factor Timing2m
Another Look at Timing the Equity Premiums5m
Macroeconomic Data5m
Designing a Factor Timing Strategy5m
Effectiveness of Factor Timing Strategies5m
Rising Interest Rates5m
FAQs on Effectiveness of Factor Timing2m
Additional Reading on Effectiveness of Factor Timing2m
Test on Factor Timing14m
- Live Trading on BlueshiftLearn 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.Section Overview2m 19s
Live Trading Overview2m 40s
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 live trading strategy template. You can tweak the code by changing securities or the strategy parameters. You can also analyse the strategy's performance in more detail.FAQs for Live Trading on Blueshift5m
Paper/Live Trading Factor Timing Strategy2m
- Factor TiltingPortfolio managers utilise techniques like factor tilting to generate alpha by strategically allocating weights to key factors. In this section, you’ll learn what factor tilting is and the basic approach to implement it.Why Factor Tilting is Required2m
Strategy Enquiry5m
Weighting Approach Used5m
What is Factor Tilting?5m
Scoring Methodology2m
Purpose of Scoring5m
Process of Selecting Top Three Assets5m
Process for Creating Scores5m
Scoring Methodology5m
FAQs on Factor Tilting2m
Additional Reading on Factor Tilting2m
Summary of Factor Tilting2m
- Creation of Portfolio EngineIn this section, we will create a portfolio engine which will serve as the framework for backtesting a factor-based portfolio.Portfolio Engine: Backtesting Framework5m
Purpose of Portfolio Engine5m
Key Benefits of the Portfolio Engine5m
First Notebook5m
Second Notebook5m
Third Notebook5m
Fourth Notebook5m
Portfolio Engine - Importing Data & Finding Rebalance Dates.5m
Portfolio Engine - Portfolio Strategy5m
Portfolio Engine - Portfolio Returns5m
Portfolio Engine - Portfolio Performance5m
- Impact of Outliers on Scoring MethodologyThe scoring approach for tilting factors is intuitive, but it can lead to overly concentrated portfolios. In this section, you'll discover how outliers can have a significant impact on portfolio weights and overall performance.Impact of Outliers on Scoring Methodology2m
Primary Risk of Overexposure5m
Diversification Importance5m
Portfolio Returns Calculation5m
FAQs on Impact of Outliers on Scoring Methodology2m
Test on Factor Tilting12m
- Rank Based Weight AllocationRank based weight allocation is popular approach used for tilting weights.Rank Based Weight Allocation2m
Ranks Order5m
Ranks Weight Diversification5m
Differences Between Consecutive Rank Weights5m
Implementing Rank Based Weight Allocation5m
Calculate Ranks5m
Rank Based Weight Allocation5m
Backtesting Rank Based Weight Allocation5m
Additional Reading on Rank Based Weight Allocation2m
- Limitations of Rank Based Weight AllocationRank based weight allocation is popular approach but comes with drawbacks.Limitations of Rank Based-Weight Allocation2m
Limitation of Rank-Based Weight Allocation5m
When to prefer score-based weight allocation?5m
Drawback of Score-Based Weight Allocation5m
FAQs on Rank Based Weight Allocation2m
Test of Rank Based Weight Allocation14m
- Process of WinsorizationBoth the scoring and ranking methods have certain limitations. Wouldn't it be great if we could somehow the best parts of both methods? In this section, we will explore the process of winsorization and check how it will help us allocate weights efficiently.
Process of Winsorization2m
Identification of Outliers5m
Percentiles in Winsorization5m
Value Below 10th Percentile5m
Advantage of Using Percentiles5m
Reason for Choosing Winsorization5m
Application of Winsorization in ETF5m
Reducing Impact of Outliers Using Winzorization5m
Pivot the ETFs Dataframe5m
Apply Winsorization on 60-Day Returns5m
Plot the KDE of Winsorized Returns5m
Backtesting with Winsorization5m
FAQs on Process of Winsorization2m
Summary of Process of Winsorization2m
Additional Reading of Process of Winsorization2m
Test on Winsorization10m
- Capstone Project on Factor CombinationIn this capstone project you will construct a factor portfolio by assigning weights to factors based on the Sortino ratio as the performance metric.Problem Statement on Factor Combination2m
- Calculation of Multiple MetricsYou have been able to create and backtest a portfolio using a single metric. Now, you will try to calculate multiple metrics which can be used later for portfolio allocation.Calculation of Multiple Metrics2m
Importance of Multiple Metrics5m
Combining Metrics for Better Decision-Making5m
Types of Metrics for Weight Allocation5m
Avoiding Redundant Metrics5m
Choosing the Right Number of Metrics5m
Practical Application of Multiple Metrics5m
Calculation of Multiple Metrics5m
FAQs on Calculation of Multiple Metrics2m
Summary of Calculation of Multiple Metrics2m
- Z-Score StandardisationIn this section, you will be able to standardise the scoring metrics using z-score.Z-Score Standardisation2m
Need for Standardisation5m
Z-Score5m
Transformed Dataset5m
Z-Score Formula5m
Calculate Z-Score5m
Z-Score Standardisation of Scoring Metrics5m
Implement Z-Score Standardisation5m
FAQs on Z-Score Standardisation2m
Additional Reading on Z-Score Standardisation2m
- Use of Z-Score Values for Weight AllocationAfter combining the z-scores of multiple metrics we have to allocate weights in proportion of their z-score values. In this section, you will see how this can be achieved.Using Z-Score Values for Weight Allocation2m
Adjustment of Z-Score Value5m
Calculation of ETF Weights5m
Use of Z-Score5m
Effect of Shifted Z-Score on Weights5m
Overall Weight Allocation Process Using Z-Scores5m
Combined Z-Score Calculation5m
Using Z-Score Values for Weight Allocation5m
Find Minimum Z-Score Value of Day5m
Calculate Shift Value5m
Shift the Z-Score Values By Calculated Shift Value5m
Calculate Sum of Z-Score Values5m
Calculate Weight of Individual Assets5m
Backtesting Using Multiple Metrics Scoring Method5m
FAQs on Using Z-Score Values for Weight Allocation2m
Summary of Using Z-Score Values for Weight Allocation2m
Additional Reading on Using Z-Score Values for Weight Allocation2m
Test on Multiple Metric Based Scoring Methodology for Factor Portfolio Creation18m
- Analyse the Performance of Multi-Factor PortfolioThis section highlights the need for a deeper analysis of portfolio performance, focusing on return consistency, concentration risks, and distribution. It emphasises diversification and introduces drawdown and stress event analysis for better risk understanding.Part Overview: Risk Assessment of Multi-Factor Portfolio2m
Performance of a Multi-Factor Portfolio2m
Need to Analyse Portfolio Returns5m
Understanding Concentration Risk5m
Mitigating Concentration Risk5m
Interpreting Skewness in Returns5m
Importance of Kurtosis in Risk Analysis5m
Takeaway from Multi-Factor Portfolio Performance5m
Risks of Over-Allocation5m
Performance Analysis of Factor Portfolio5m
Calculate the Cumulative Metrics5m
Calculate Daily Volatility5m
Calculate the Returns Metrics5m
Plot the Returns Histogram5m
FAQs on the Performance of a Multi-Factor Portfolio2m
Additional Reading on Performance of a Multi-Factor Portfolio2m
Summary of Performance of a Multi-Factor Portfolio2m
Test on Performance of a Multi-Factor Portfolio16m
- Analyse the Drawdowns of Multi-Factor PortfolioThis section discusses in-depth risk analysis, focusing on drawdowns, recovery times, and the impact of market events. It concludes with an introduction to analysing portfolio sensitivity to factors.Drawdown Analysis of a Multi-Factor Portfolio2m
Importance of Drawdown Analysis5m
Evaluating Top 5 Drawdowns5m
Understanding Recovery Times5m
Analysing Recovery of the October 2022 Drawdown5m
Identifying Market Stress Events5m
Sensitivity to Factors5m
Drawdown Analysis of Factor Portfolio5m
Calculate the Drawdown5m
Calculate the Max Drawdown Date5m
Calculating Recovery Date5m
Calculating Recovery Duration5m
FAQs on the Drawdown Analysis of a Multi-Factor Portfolio2m
Additional Reading on Drawdown Analysis of a Multi-Factor Portfolio2m
Summary of Drawdown Analysis of a Multi-Factor Portfolio2m
Test on Drawdown Analysis of a Multi-Factor Portfolio14m
- Analyse the Sensitivity of Portfolio to its FactorsThis section explains how to measure portfolio sensitivity using factor beta, which shows how returns change with factor shifts. It uses linear regression for calculation and highlights that growth and momentum factors are key drivers of portfolio returns.Sensitivity of Portfolio to its Factors2m
Importance of Factor Beta5m
Interpreting Factor Beta Value5m
Method for Measuring Factor Beta5m
Linear Regression Equation5m
Factor Beta for a Multi-Factor Portfolio5m
Interpreting Factor Beta Plot5m
Calculate and Interpret Factor Beta5m
Check Index Alignment5m
Calculate the Factor Beta5m
FAQs on the Sensitivity of Portfolio to its Factors2m
Additional Reading on Sensitivity of Portfolio to its Factors2m
Summary of Sensitivity of Portfolio to its Factors2m
Test on Sensitivity of Portfolio to its Factors14m
- Core and Satellite InvestingCore and Satellite investing blends stability and growth by combining a diversified core for steady returns with satellite investments for higher growth potential.Core and Satellite Investing2m
Approaches in Core and Satellite Investing5m
Fast-moving vs Slow-moving satellite5m
Best Composition5m
FAQs on Core and Satellite Investing2m
Additional Reading on Core and Satellite Investing2m
- Factor Investing in Emerging MarketsIn this section, we will examine how factors in developing markets behave differently compared to the developed markets. We will discuss the unique challenges and opportunities, including market inefficiencies, liquidity constraints, and macroeconomic influences.Factor Investing in Emerging Markets2m
Key Reason for Factor Investing5m
Rapid Growth of Emerging Markets5m
Major Challenge5m
Effectiveness of Factor Investing5m
Unique Growth Theme5m
FAQs on Factor Investing in Emerging Markets2m
Additional Reading on Factor Investing in Emerging Markets2m
- Limitations of Factor InvestingUnderstand the key challenges of factor investing, including data mining, specification errors, crowding, regime shifts, and overfitting. Learn strategies to mitigate these issues.Limitations of Factor Investing2m
Historical Data5m
Mitigate the Risk of Data Mining5m
Specification Error5m
Price-To-Earnings Ratio5m
Low-Volatility Factor Strategy5m
FAQs on Limitations of Factor Investing2m
Additional Reading on Limitations of Factor Investing2m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.Uninterrupted Learning Journey with Quantra2m
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
- Summary of the CourseIn this section, you will go through the summary of the course and access the data files and notebooks which were used in the course.Summary of the Course2m
Summary of the Course and Next Steps2m
Python Codes and Data2m
Portfolio Management using Machine Learning: Hierarchical Risk Parity
- IntroductionThe ability of unsupervised learning to find similar patterns and group assets can be harnessed in the field of portfolio management with ease. 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.
- Portfolio Basics and Stock ScreeningA collection of the assets in your possession is called a portfolio. In this section, the importance of diversification is discussed. A simple portfolio management technique called the equal-weighted method is covered in brief. But before implementing a strategy, you need to select the assets you will be using for the strategy. For that, we have applied several filters on the S&P 500 stocks to shortlist 16 stocks for the portfolio.Portfolio Diversification3m 15s
How to allocate capital?2m
Why should you diversify?2m
Stock Screener10m
Read the Price Data5m
Filter Stocks on Liquidity5m
Filter Stocks on Momentum5m
Filter Stocks on Fundamental Factor5m
Get Market Data10m
Equal Weight Portfolio10m
Equal Weight Calculation5m
Sharpe Ratio Calculation5m
Portfolio Return Calculation5m
Additional Reading on Equal Weights Portfolio10m
- Inverse Volatility PortfoliosAnother approach to asset weight allocation is by considering the risk associated with the asset. The inverse volatility portfolio tries to give more weightage to less volatile, or less risky, assets.Role of Volatility in Measuring Risk1m 58s
Limitations of Equal Weight Portfolio2m
Identifying Volatile Stocks2m
Risk Contribution of Assets2m
Differentiating Low and High Volatile Stocks2m
Allocating Weights Using Volatility2m 25s
Measurement of Volatility2m
Use of Inverse Volatility2m
Calculation of Inverse Volatility2m
Percentage Capital Allocation Using IVP2m
Capital Allocation Using IVP2m
- Implementing Inverse Volatility PortfoliosIn this section, we apply the inverse volatility based weight allocation technique on a set of 16 stocks using risk as a metric. We also see its performance on past data.Inverse Volatility on Three Stocks1m 59s
Exclusions in Inverse Volatility Portfolio2m
Assets Allocation Using IVP2m
Asset Weight Calculation Using IVP2m
Limitation of IVP2m
Inverse Volatility Portfolio10m
Calculate the Monthly Prices5m
Split the Data5m
Inverse Volatility Weight Calculation5m
Additional Reading10m
- CorrelationIn simple terms, correlation is used to measure how two assets move with respect to each other. Correlation is a standardised measure which gives a score between -1 and 1. In this section, you will test different assets and find their correlation scores.Correlation10m
Covariance Calculation5m
Correlation Calculation5m
Impact of Correlated Stocks on Portfolio’s Performance3m 7s
Optimal Weight Allocation2m
Select Assets2m
Choose Portfolio2m
Additional Reading10m
- Markowitz Critical Line AlgorithmApart from risk, Markowitz suggested that returns is also an important metric to focus on. He suggested that the portfolio with optimal weights would have the highest return per unit of risk. In this section, we understand how the critical line algorithm works to find the optimal portfolio weights.Intuition of Critical Line Algorithm2m
Return vs Risk2m
Choose Portfolio Part-12m
Choose Portfolio Part-22m
Choose Portfolio Part-32m
Selecting the Most Optimal Weights4m 35s
Optimal Portfolio2m
Increase Return:Risk Ratio2m
Efficient Frontier2m
Find 15% Volatility Portfolio2m
- Implementing CLAIn this section, we use the concept of critical line algorithm (CLA) and implement it on a set of 16 stocks. We also assess its performance over unseen data.Critical Line Algorithm10m
Random Weights Allocation5m
Returns per Unit of Risk5m
Find the Optimal Portfolio5m
Limitations of Critical Line Algorithm2m 52s
Difference in Return2m
Concentrated Portfolio2m
Concentration of Weights2m
Limitations of CLA2m
Additional Reading10m
Test on IVP and CLA16m
- Hierarchical ClusteringThis section will focus on giving you an intuition of the unsupervised learning technique of hierarchical clustering. Developing from the basics, you will see how exactly a meaningful hierarchy can be created for financial stock data.
What is Hierarchical Clustering?1m 55s
Clustering2m
Correct Hierarchy2m
Hierarchical Clustering On Stocks3m 40s
Clustering Two Stocks2m
Features for Grouping2m
Dendrogram2m
Type of Hierarchical Clustering2m
Output of Different Techniques2m
Additional Reading10m
- Mathematics Behind Hierarchical ClusteringNow that you have been introduced to the world of hierarchical clustering, in this section you will dive deep into the mathematics behind it all. Many concepts including the euclidean distance and proximity matrix will be covered so that you know the details behind the black box.Euclidean Distance Between Points3m 18s
Distance Between Multiple Dimensions2m
Euclidean Distance2m
Implementing Hierarchical Clustering2m
Cluster Composition2m
Distance Using Proximity Matrix2m
Correct Proximity Matrix2m
Complete the Proximity Matrix2m
Forming a New Cluster2m
Combining Two Clusters2m
Zero Diagonal2m
Additional Reading10m
Test on Hierarchical Clustering18m
- Clustering with DendrogramsIn this section you will learn to visualise the hierarchy of clusters using Python. You will be introduced to specific functions in the SciPy library that will help you create meaningful clusters. The code will introduce you to linkaging and distance measures that you can use to create your dendrogram.Dendrograms2m 7s
Distance Between Clusters2m
Dendrogram Output2m
Clustering with Dendrograms10m
What is Linkage Matrix2m
Use of Ward’s Method2m
Create a Linkage Matrix5m
Plot Dendrogram5m
Additional Reading10m
- Scaling Your DataScaling is an important concept whenever it comes to unsupervised learning and clustering in general. In this section, you will implement the standard scaling technique on your dataset after learning about its importance in hierarchical clustering. By the end of this section you will be armed with everything you need to create a portfolio using hierarchical clustering.Importance of Scaling3m 27s
Correct Clustering2m
Value Range2m
Sensitivity of Euclidean Distance2m
Scaling Your Data2m 40s
Value Range with Scaling2m
Scale Two or More Features2m
Standard Scaling2m
Calculate Scaled Value2m
Properties of Standard Scaling2m
Importance of Scaling the Data10m
Standard Scaling the Data5m
Additional Reading10m
- Hierarchical Risk ParityThe final section on hierarchical clustering will introduce you to the concept of Hierarchical Risk Parity. It is the methodology of creating a risk-based portfolio that has been allocated capital based on meaningful similarity between the stocks. The section will end with a performance comparison of the portfolio based on all the techniques that you have learnt, i.e., Equal Weights, Inverse Volatility, Critical Line Algorithm and Hierarchical Risk Parity.Weight Allocation3m 43s
Divide Into Groups2m
Calculate Weights Using Inverse Volatility2m
Total Allocation to a Group2m
When to Stop2m
Zero Allocation2m
Assign Weights2m
Data Preparation and Plotting Dendrogram10m
Weights Allocation and Portfolio Evaluation10m
Cluster Volatility5m
Agglomerative Clustering5m
Assigning Weights to Clusters5m
Comparing Different Portfolio Techniques10m
Assigning Upper Limit for Weights10m
Additional Reading10m
Test on Dendrograms, Data Scaling and Hierarchical Risk Parity18m
- Live Trading on BlueshiftThis section walks you through the steps involved in taking your trading strategy live. You will learn about backtesting on Blueshift. It also includes 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 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 Weight Allocation using HRP10m
FAQs for Live Trading on Blueshift10m
- Capstone ProjectIn this section, you will undertake a capstone project where you apply the k-means algorithm on the stock of your choice. This project helps you to practice and apply the concepts learnt in this course.Capstone Project: Getting Started10m
Problem Statement10m
Frequently Asked Questions10m
Code Template and Data Files2m
Capstone Project Model Solution10m
Capstone Solution Downloadable2m
- Run Codes Locally on Your MachineThis section includes the installation of 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
Installing Ta-Lib2m
Quantra Environment2m
Troubleshooting Tips For Setting Environment10m
How to Run Files in Download Section?10m
Troubleshooting For Running Files in Download 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 Summary-I7m 19s
Course Summary-II4m 38s
Python Codes and Data2m
AI Portfolio Management with LSTM Networks & Hyperparameter Sweep
- IntroductionThis 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 artificial intelligence. 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.
- Aim of Portfolio ManagementWhat should you look for when you are trying to create a portfolio? Returns? Risk? In this section, you will go through a scenario where you will understand what is to be considered when creating your own portfolio. You will also look at the mean-variance ratio and how it can be used to create an optimal portfolio.
Aim of Portfolio Management2m
Consideration in Creation of Portfolio5m
Key Characteristic of Portfolio5m
Analogy of Portfolio5m
Portfolio Choices5m
Optimisation of a Portfolio2m
Portfolio Optimisation Using Risk or Return5m
Equal Importance to Risk and Return5m
Measure of Risk and Return5m
Mean-Variance Ratio5m
Mean-Variance and Sharpe Ratio5m
Portfolio Choice Using Mean-Variance Optimisation5m
Compatibility of Measures5m
Decision Between Two Portfolios5m
Section Summary2m
Additional Reading2m
FAQ2m
Understanding Aim of Portfolio Management5m
- Building a PortfolioHow many different variations of portfolio weights should you consider while optimising your portfolio? If your answer is in single digits, you might be in for a surprise in this section. With the use of Python libraries, you can consider a large number of portfolio variations with different portfolio weights.Optimisation of Portfolio Using Mean-Variance2m
Multiple Portfolios5m
Generation of Multiple Portfolios5m
Equal Mean-Variance Ratios5m
Steps to Create Mean-Variance Optimised Portfolio5m
Application of Mean-Variance Optimisation5m
Equal Returns of Two Portfolios5m
Choice of Portfolio5m
- Walk Forward OptimisationIn this section, you will try to see how you can use a major part of the dataset for optimisation without falling prey to overfitting or look-ahead biases.Walk Forward Optimisation2m
Backtesting Entire Data5m
Drawback of Division of Dataset in Two Parts5m
Usage of Walk Forward Optimisation5m
Concept of Walk Forward Optimisation5m
Application of Mean-Variance on Data5m
Advantage of Walk Forward Optimisation5m
Walk Forward Optimisation with Fixed Window2m
Significance of Fixed Window5m
Assignment of Weights5m
Recalculation of Optimal Weights5m
Portfolio Return Calculations5m
Increase in Fixed Window Size5m
Performance of Asset and Optimisation Process5m
FAQ2m
- Application of Mean-Variance in PortfolioYou have understood the mean-variance ratio for the calculation of optimal portfolio weights. You also saw how walk-forward optimisation can use a major part of the dataset for training without running into biases. Now, you will apply all your knowledge and create your very own mean-variance-based optimised portfolio.How to Use Jupyter Notebook?1m 54s
Optimise Weights in Portfolio5m
Calculate Daily Portfolio Returns5m
Calculate Negative Sharpe Ratio5m
Call Minimize Function5m
Call Get Optimal Weights Function5m
Calculate Sum of Weights for a Particular Day5m
Part Summary2m
Additional Reading2m
Frequently Asked Questions2m
- Different Types of PortfolioIn this section, you will create different types of portfolios considering the short and long components of the portfolio. You will also see how leverage impacts the portfolio returns.Different Types of Portfolio2m
Optimisation Method for Portfolio Management5m
Improvement of Portfolio Returns5m
Addition to Portfolio Returns5m
Build and Optimise Long Short Portfolios5m
Summary of Mean-Variance Optimised Portfolio2m
Additional Reading2m
FAQ2m
Test on Mean-Variance Optimised Portfolio16m
- AI for Portfolio OptimisationUntil now, we implemented portfolio optimisation using the mean-variance method, which is a traditional portfolio optimisation method. Are there any other ways to optimise the portfolio? In this section, we will explore the concept of artificial intelligence and how it can be used for portfolio optimisation.
AI for Portfolio Optimisation2m 15s
Advantage of Using Artificial Intelligence5m
Informative Features5m
Capturing Market Movements5m
Distribution of Asset Returns5m
Temporal Aspects of Financial Data5m
Artificial Intelligence2m 12s
Goal of Artificial Intelligence5m
Self-Driving Cars5m
Voice Assistants5m
AI-Driven Portfolio Management Systems5m
Categories of AI Models5m
Additional Reading on AI for Portfolio Optimisation2m
- Artificial Neural NetworksIn this section, we explain the architecture of artificial neural network and its key components like neurons, activation functions and optimisers.ANN Architecture2m
Role of Activation Functions5m
Purpose of Weights5m
Learning Process5m
Neural Network Optimizer5m
Portfolio Optimization - ANN5m
Activation Functions2m
Optimizers2m
Drawback of ANN2m
Test on AI for Portfolio Optimisation and ANN14m
- Long Short-Term Memory For Portfolio OptimisationIntroduction of Long Short-Term Memory(LSTM) neural network for application in portfolio management. This section covers the differences between ANN and LSTM.Differences Between ANN and LSTM3m 04s
ANN for Portfolio Optimisation5m
Memory Cells of LSTM Networks5m
LSTM vs ANN for Time Series Data5m
Structural Differences Between ANN and LSTM Networks5m
LSTM for Portfolio Optimisation5m
FAQs on Long Short-Term Memory For Portfolio Optimisation2m
Additional Reading for Long Short-Term Memory For Portfolio Optimisation2m
- Set Up LSTM Network for Portfolio OptimisationThis section covers the concepts used to create an LSTM network and structure the network for portfolio optimisation.
How to Set Up the LSTM Network?2m
Setting Up LSTM for Portfolio Optimisation5m
Batch Size in LSTM Networks5m
Input Data Dimensions in LSTM Networks5m
Loss Function in LSTM Networks5m
Customised Loss Function5m
LSTM for Portfolio Weights Optimisation5m
Determining Optimal Output Node Size in LSTM Input Layer5m
Defining Input Shape for Time Series Data in LSTM5m
Understanding the 'Sequential' Function in LSTM Model Syntax5m
Purpose of the Output Layer in Neural Networks and LSTM5m
Determining Output Layer Size in the LSTM Model5m
Choosing 'Softmax' for LSTM Output Layer Activation5m
Functionality of Softmax in Normalising LSTM Output Layer5m
Benefits of Softmax in Determining Portfolio Weights5m
Default Activation Function in LSTM Output Layer5m
Updating LSTM Model with a New Layer: Keras Syntax5m
- LSTM implementation for Portfolio optimisationThis section covers the implementation of LSTM neural networks for portfolio optimization. In addition to a detailed explanation on how to set up an LSTM network, this section also contains the Python implementation of LSTM for Portfolio Optimization.Implementing LSTM for Portfolio Weights Optimisation5m
Create the Features Data5m
Initialising the Model Class5m
Assigning Upper Limit for Weights5m
FAQs on LSTM Implementation For Portfolio Optimisation2m
Additional Reading on LSTM implementation for Portfolio Optimisation2m
- Live Trading on IBridgePyIn 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 Quantra2m
Section Overview2m 2s
Live Trading Overview2m 41s
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 TradingTo 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 Documentation10m
Template Code File2m
- Walk Forward Optimisation With LSTMThis section covers the implementation of walk forward optimisation, a way to realistically understand the performance of the portfolio in the history. The complete implementation of walk forward optimisation along with quiz questions is covered in this question.
- Hyperparameter SweepThis section covers the concepts of hyperparameter sweep and how it is used to select the hyperparameters of LSTM implementation for portfolio optimisation along with walk forward optimisation.Hyperparameter Sweep2m
Understanding Hyperparameters in LSTM for Portfolio Optimisation5m
Right Analogy for Hyperparameters5m
Understanding the Hyperparameter Sweep Process5m
Purpose of Hyperparameter Sweep in Portfolio Optimisation5m
Term for Trying Different Hyperparameter Combinations5m
Hyperparameter Sweep of LSTM and Walk Forward Optimisation5m
Function to Optimise During Hyperparameter Sweep5m
Selecting the Best Hyperparameters5m
Test on Building LSTM Model for Portfolio Management14m
FAQs on Hyperparameter Sweep2m
Additional Reading on Hyperparameter Sweep2m
- Capstone Project-1In this section, you will apply the knowledge you have gained in the course so far. You will pick up a capstone project where you create a custom loss function for the LSTM model to calculate optimum weights for the assets in the portfolio.Getting Started With Capstone Project2m
Problem Statement2m
Code Template and Data2m
Capstone Solution2m
- Building Long-Short LSTMBy now you already know how to build an LSTM model to optimise a long-only portfolio. In this section, we will take things up a notch by modifying the existing LSTM model such that it can optimise a long/short portfolio.LSTM for Long-Short Portfolio: An Overview2m
Getting Weights for Long-Short Portfolio2m
Issue with the Existing Model5m
Identify the Modification5m
Net Weights5m
Positive Net Weights5m
Number of Weights5m
Identify Long Positions5m
Modifications to LSTM2m
Identify the Modifications5m
Weights for Four Assets5m
Number of Weights for Long/Short Portfolio5m
Dual Weights5m
Role of Net Weights5m
Calculation of Sharpe Ratio5m
Adjusting the Weights5m
Final Output5m
Core Goal of the Model5m
Optimisation Process5m
- Implementing LSTM for Long-Short PortfolioThis section covers the Python implementation of the new LSTM model. In this section, you will learn how to make modifications to the long-only LSTM model and calculate weights for a long-short portfolio. You will also assess the results of the long-short optimised portfolio against the benchmark portfolio.Build the Model2m
LSTM Model for Long-Short Portfolio5m
Long Side of the Portfolio5m
Difference between Long and Short Side5m
Building the Model5m
Portfolio Optimisation for Tech Stocks5m
Identify the Net Weights5m
Identify the Sharpe Ratio5m
Additional Reading on LSTM for Long/Short Portfolio Optimisation2m
FAQs on LSTM for Long/Short Portfolio2m
Test on LSTM for Long-Short Portfolio10m
- Capstone Project - 2In this section, you will apply the concepts learned in the past two sections. This project requires you to create an optimised long-short portfolio using the new LSTM model. But this time you will create a portfolio with a diversified range of assets instead of just stocks.Problem Statement2m
Code Template and Data Files2m
Capstone Project Model Solution5m
Capstone Solution Downloadable2m
- Increasing the Features in the LSTM ModelIn this section, you will add some additional features to the existing LSTM model and create a long/short portfolio of tech stocks.Increasing the Features in the LSTM Model5m
Model Architecture5m
Data Splitting5m
Feature Creation5m
Feature Significance5m
Random Seed Usage5m
- Run Codes Locally on Your MachineLearn to install the Python environment in your local machine.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
- Summary and Next StepsIn this section, you will summarise the key concepts covered in the course and what you can do further in the realm of algo trading using AI.Summary and Next Steps2m
Next Steps2m
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.
Quantpedia
Quantpedia is the encyclopedia/database of quantitative and algorithmic trading strategies. It helps users in processing financial academic research into a more user-friendly form to help anyone who seeks new quantitative trading strategy ideas.
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
Fund manager at Morabanc Asset Management, Andorra
A best in class introductory course to quantitative portfolio management. Learning from the very first minute with Python language, from capital allocation methods to risk metrics, without forgetting asset pricing models and factor investing. Easy to progress, full of practice, programming exercises, and quite a remarkable synthesis of concepts to make comprehension, capabilities, and limitations of its quantitative tools a key factor.
Trader, Italy
The course offers a simple but effective introduction to quantitative portfolio management by providing the fundamental concepts of capital allocation, factor investing, and performance analysis; specifically, the theory is followed by Python code that clearly implements the explained concepts. The course results in practical skills that constitute the basis for professional quantitative portfolio management.
Senior Professor, Singapore
Very good!!
Trader, India
Quantra is the best platform I have come across for online courses on Algo & Quant trading. The courses make difficult concepts very easy to understand by their good visual examples and interactive learning.
Technical Analyst, India
The course was no doubt good, the videos helped a lot, it's like you are in a classroom with the teachers teaching you. The MCQs are thought provoking, the answers may look simple at first, but once you start thinking, you know it is a smart question, something that will help you remember the answer for long!
United States
Very clear and instructive explanations.
VR
United Kingdom
Great Course!
RG
IOS developer, Ex Pandora, United States
With the experience of All Courses Bundle (50+ courses) said - "Quantra was my one-stop solution for algo trading. Based on the courses I have completed, Quantra has exceeded my expectations. For me, Quantra’s best feature has to be the flexibility it offers. All courses on the platform are self-paced, meaning I can learn, practice, improvise and go back to learning whenever I want."
DD
United States
Everything was good
NG
Spain
More than expected
LG
Portfolio Manager, France
Very Interesting Subject
PG
Australia
Great course and very helpful learning materials
LM
Macao
Great insight for the porfolio construction skill!
LC
Brazil
Very insightful course
MP
United Kingdom
I like all the pos sizing concepts!
VZ
Japan
A piece of knowledge every trader should learn as soon as possible, clearly exposed. Unlike most materials on trading that talk about improving one's edge, this is about using what edge you have as safely and efficiently as possible.
AC
Data Analyst, India
The course was holistic.
AP
Germany
Very good! It explains metrics and risk management models in a very consistent way.
JS
Analyst at Phoenix Group, South Africa
Course was Insightful
BS
United States
Educative course!
AB
Professor, Instituto Superior Técnico, Portugal
The concepts and ideas presented are excellent, and are well explained in the videos and comments available
SW
Australia
great self-paced course, used different teaching techniques and reinforcements.
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 ₹10168/month for 6 months
Available through our partner NBFC
₹51700₹258494
