← Back to Curriculum

Intermediate

Building a Portfolio Optimizer Using Python's PyPortfolioOpt

A hands-on build course for quant aspirants, prop desk applicants and traders who want to systematise how they size a portfolio. You already know what an efficient frontier is. This course makes you build one that survives contact with real Indian data. You will pull a clean price panel for Nifty 50 stocks, estimate expected returns three ways, build covariance matrices that are not drowned in noise, and run max Sharpe, minimum volatility and target return optimisations in PyPortfolioOpt with the Indian risk-free rate. You then add the constraints a real portfolio needs (weight caps, NSE sector limits, regularisation, transaction cost penalties), move beyond mean-variance with Hierarchical Risk Parity, Black-Litterman and CVaR, and finally convert weights into whole shares for a real INR budget, backtest the result against the Nifty 50 TRI and account for rebalancing turnover and Indian capital gains tax. The course ends with an end-to-end monthly optimizer pipeline you can rerun yourself.

PyPortfolioOptExpected Returns EstimationCovariance and ShrinkageEfficient FrontierMax Sharpe and Min VolatilityPortfolio ConstraintsHierarchical Risk ParityBlack-LittermanCVaR OptimisationDiscrete AllocationRebalancing and Tax Drag

MODULES

7

DURATION

4 Hours

TRACK

Python for Finance

What You'll Master

Set up a reproducible PyPortfolioOpt project and build a clean, adjusted price panel for NSE stocks

Estimate expected returns with historical, exponentially weighted and CAPM methods, and know why each one misleads

Build sample, shrunk, exponential and semicovariance risk models, and check them before trusting them

Run max Sharpe, minimum volatility and target return optimisations using the Indian risk-free rate, and plot the efficient frontier

Add weight bounds, NSE sector limits, L2 regularisation and transaction cost penalties so the optimizer produces investable portfolios

Apply Hierarchical Risk Parity, Black-Litterman and CVaR optimisation, and choose between optimisers with evidence

Convert weights into whole-share orders for an INR budget, and backtest the portfolio fairly against the Nifty 50 TRI

Design rebalancing rules that account for turnover, brokerage and Indian capital gains tax, inside one rerunnable pipeline

Access Level

LEARNER

Start Learning Now →Sign in to resume

Everything included

Full Text Playbooks

Actionable Exercises

Mobile Reading Mode

Lifetime Updates

Curriculum Breakdown

Chapter 1: Setting Up the Optimizer Project

4 Lessons

Why PyPortfolioOpt: From Markowitz Theory to Working Code10 min read

Installing PyPortfolioOpt and Structuring an Optimizer Project11 min read

Building a Clean Adjusted Price Panel for Nifty 50 Stocks13 min read

The Three Optimizer Inputs: Expected Returns, a Risk Model and Constraints11 min read

Chapter 2: Estimating Expected Returns

4 Lessons

Mean Historical Returns in PyPortfolioOpt and Why They Mislead12 min read

Exponentially Weighted Returns for Indian Stocks11 min read

CAPM Expected Returns With the Nifty 50 as the Market12 min read

Sanity-Checking Return Estimates Before You Optimise11 min read

Chapter 3: Building the Risk Model

4 Lessons

The Sample Covariance Matrix and the Noise Hiding in It12 min read

Ledoit-Wolf Shrinkage With PyPortfolioOpt's CovarianceShrinkage12 min read

Exponential Covariance and Semicovariance for Downside-Aware Risk12 min read

Visualising and Validating a Covariance Matrix Before Optimising11 min read

Chapter 4: Mean-Variance Optimisation With EfficientFrontier

4 Lessons

Max Sharpe Portfolios Using the Indian Risk-Free Rate13 min read

Minimum Volatility, Efficient Risk and Efficient Return Portfolios12 min read

Plotting the Efficient Frontier for a Nifty 50 Universe in PyPortfolioOpt12 min read

Cleaning Weights and Reading PyPortfolioOpt's Performance Output11 min read

Chapter 5: Constraints That Match Real Portfolios

4 Lessons

Weight Bounds, Long-Only Rules and Position Caps in EfficientFrontier12 min read

Sector Constraints Using NSE Industry Classifications12 min read

L2 Regularisation to Stop Corner-Solution Portfolios11 min read

Custom Objectives and Transaction Cost Penalties in PyPortfolioOpt13 min read

Chapter 6: Beyond Mean-Variance

4 Lessons

Hierarchical Risk Parity With HRPOpt on NSE Stocks13 min read

Black-Litterman in PyPortfolioOpt: Blending Market Priors With Your Views14 min read

Efficient CVaR and Efficient Semivariance Optimisation12 min read

Choosing an Optimiser: A Side-by-Side Comparison on One Nifty 50 Universe12 min read

Chapter 7: From Weights to a Live Portfolio

4 Lessons

Discrete Allocation: Turning Optimizer Weights Into Whole NSE Shares12 min read

Backtesting an Optimised Portfolio Against the Nifty 50 TRI13 min read

Rebalancing Optimised Portfolios: Turnover, Brokerage and Capital Gains Tax Drag13 min read

Capstone: An End-to-End Monthly PyPortfolioOpt Pipeline15 min read