Quantitative Trading Strategies

"Quantitative Trading Strategies: Applying Tree-Based and Linear Models"
Quantitative Trading Strategies: Applying Tree-Based and Linear Models is a practical guide for quants, systematic traders, and data-driven portfolio managers who want to design, test, and deploy robust trading strategies. Bridging statistical rigor with market reality, the book walks readers from foundational mathematics and market structure through to fully specified, execution-aware strategies. It is written for practitioners and advanced students who seek to move beyond ad hoc backtests and toward disciplined, model-based trading research.
The book develops a complete workflow for building signals with linear and tree-based models, including OLS, regularized regression, decision trees, random forests, and gradient boosting. Readers will learn how to engineer predictive features from financial time series, frame problems as regression or classification, and perform time-aware hyperparameter tuning and model interpretation. Dedicated chapters cover data integrity, time-series cross-validation, event-driven backtesting, transaction cost modeling, portfolio construction, and risk and performance attribution, culminating in realistic case studies that tie all components together.
Assuming comfort with basic probability, statistics, and Python, the text deepens these skills in a focused, market-centric context. Presented in a LaTeX-friendly structure with clear notation and self-contained sections, it emphasizes reproducibility, governance, and implementation details often glossed over in academic tre