Machine Learning for Algorithmic Trading - Second Edition
- 820 stránek
- 29 hodin čtení
Leverage machine learning to design and back-test automated trading strategies for real-world markets using tools like pandas, TA-Lib, scikit-learn, LightGBM, SpaCy, Gensim, TensorFlow 2, Zipline, backtrader, Alphalens, and pyfolio. This revised second edition equips you to build and evaluate sophisticated supervised, unsupervised, and reinforcement learning models, introducing an end-to-end machine learning workflow for trading. From idea generation and feature engineering to model optimization, strategy design, and backtesting, it covers a range of techniques from linear models to deep learning. You’ll learn to work with various data types, including market, fundamental, and alternative data—such as tick data, SEC filings, earnings call transcripts, and financial news—to extract tradeable signals. The book illustrates how to engineer financial features or alpha factors that enable ML models to predict returns for US and international stocks and ETFs. It also teaches how to assess new features' signal content using Alphalens and SHAP values. By the end, you’ll be adept at translating ML predictions into trading strategies for daily or intraday operations and evaluating their performance. You will learn to leverage diverse data, research alpha factors, implement ML techniques for investment problems, backtest strategies, and optimize portfolio performance.


