Quantitative Portfolio Management with Python

Bridge the Gap Between Portfolio Theory and Practical Python Code

Modern quantitative portfolio management sits at the intersection of rigorous mathematical theory and real-world execution. Yet, most financial literature forces a compromise: books either present heavy linear algebra without executable code, or offer code snippets stripped of theoretical derivations.

Written by Dr. Ahmet Goncu, professor of finance and PhD in financial mathematics, Quantitative Portfolio Management with Python bridges this gap completely. From foundational mean-variance optimization to advanced machine learning and reinforcement learning algorithms, every equation is derived step-by-step and implemented from scratch in Python.

What You Will Learn:

• Foundations of Portfolio Mathematics: Master matrix calculus, quadratic forms, and Lagrangian optimization applied to minimum-variance and tangency portfolios.

• Asset Pricing & Factor Models: Build, estimate, and evaluate the Capital Asset Pricing Model (CAPM) and Fama-French multi-factor regressions on real market data.

• Advanced Portfolio Construction: Address classical mean-variance estimation error using Ledoit-Wolf covariance shrinkage, Black-Litterman Bayesian inference, and Hierarchical Risk Parity (HRP).

• Machine Learning & Reinforcement Learning: Formulate state-space representations and train REINFORCE-based reinforcement learning agents for dynamic allocation.

• Walk-Forward Backtesting: Implement rigorous walk-forward backtesting frameworks to stress-test equity, bond, and commodity portfolios.

Key Features:

• Self-Contained Python Code: All code listings use standard scientific libraries (numpy, pandas, scipy, scikit-learn, statsmodels, yfinance) and run out-of-the-box.

• No Black-Box Wrappers: Every key algorithm—from Black-Litterman posterior estimation to Hierarchical Risk Parity recursive bisection—is built from first principles.

• Preliminary Math Foundations: Includes a comprehensive linear algebra refresher and standalone appendices covering optimization, statistics, and setup.

Whether you are a graduate student in financial engineering, a quantitative researcher, a risk manager, or a practitioner looking to modernize your backtesting stack, this textbook provides the mathematical foundation and pythonic tools required to excel in modern quantitative finance.