Advances in Financial Machine Learning
An influential and demanding treatment of how machine learning should — and should not — be applied to financial data, with particular attention to backtest overfitting.
Books our editors consider essential background for systematic trading, risk and market structure. Listed for education only; we receive nothing for these recommendations.
An influential and demanding treatment of how machine learning should — and should not — be applied to financial data, with particular attention to backtest overfitting.
A practical, code-heavy survey of the full pipeline from data to models to backtesting, accompanied by extensive notebooks. The author also maintains Zipline Reloaded.
An accessible introduction to running a quantitative trading operation as an individual, covering strategy discovery, backtesting and execution.
A clear framework for designing systematic strategies and portfolios, with a strong focus on position sizing and avoiding overfitting.
A non-technical explanation of how quantitative trading firms are structured and how their systems fit together.
Explores mean-reversion and momentum strategies with emphasis on the reasoning behind them rather than mechanical rules.
Applies scientific method and statistical inference to technical analysis, including data-mining bias and how to correct for it.
The standard reference on how markets work: order types, liquidity, market makers and trading costs.
A comprehensive review of the evidence on return sources across asset classes and strategy styles.
A foundational, quantitative text on forecasting, portfolio construction and the measurement of skill.
The widely used textbook on derivatives pricing and risk; essential background for anyone working with options or futures. Multiple editions.
An essay on the role of chance in markets and the human tendency to mistake luck for skill.