This second edition adds a ton of examples that illustrate the ML4T workflow from universe selection, feature engineering and ML model development to strategy design and evaluation. A new chapter on strategy backtesting shows how to work with backtrader and Zipline, and a new appendix describes and tests over 100 different alpha factors. The book also replicates research recently published in top journals on topics such as extracting risk factors conditioned on stock characteristics with an autoencoder, creating synthetic training data using GANs, and applying a CNN to time series converted to image format to predict returns. The strategies now target asset classes and trading scenarios beyond US equities at a daily frequency, like international stocks and ETFs or minute-frequency data for an intraday strategy. It also expands coverage of alternative data such as SEC filings to predict earnings surprises, satellite images to classify land use, or financial news to extract topics.