What's new in the second edition

This second edition emphasizes the end-to-end ML4T workflow, reflected in a new chapter on strategy backtesting (Chapter 8, The ML4T Workflow – From Model to Strategy Backtesting), a new appendix describing over 100 different alpha factors, and many new practical applications. We have also rewritten most of the existing content for clarity and readability.

The applications now use a broader range of data sources beyond daily US equity prices, including international stocks and ETFs, as well as minute-frequency equity data to demonstrate an intraday strategy. Also, there is now broader coverage of alternative data sources, including SEC filings for sentiment analysis and return forecasts, as well as satellite images to classify land use.

Furthermore, the book replicates several applications recently published in academic papers. Chapter 18, CNNs for Financial Time Series and Satellite Images, demonstrates how to apply convolutional neural networks to time series converted to image format for return predictions. Chapter 20, Autoencoders for Conditional Risk Factors and Asset Pricing, shows how to extract risk factors conditioned on stock characteristics for asset pricing using autoencoders. Chapter 21, Generative Adversarial Networks for Synthetic Time-Series Data, examines how to create synthetic training data using generative adversarial networks.

All applications now use the latest available (at the time of writing) software versions, such as pandas 1.0 and TensorFlow 2.2. There is also a customized version of Zipline that makes it easy to include machine learning model predictions when designing a trading strategy.