Machine Learning for Algorithmic Trading

Stefan is the CEO and creator of Applied AI. He consults Fortune 500 businesses, investment firms, and startups across industries on data and AI strategy, team building, and implementing end-to-end machine learning solutions for a wide range of business problems.

The increasing rise of digital data has increased the demand for competence in machine learning trading tactics (ML). You can develop and assess powerful supervised, unsupervised, and reinforcement learning models with this rewritten and enlarged second edition.

Machine Learning for Algorithmic Trading covers the entire trading workflow, from idea and feature engineering to model optimization, strategy creation, and backtesting. It demonstrates this with examples ranging from linear models and tree-based ensembles to cutting-edge deep-learning approaches.

This edition demonstrates how to develop tradeable signals using market, fundamental, and alternative data such as tick data, minute and daily bars, SEC filings, earnings call transcripts, financial news, or satellite photos. It demonstrates how to create financial features or alpha factors that allow a machine learning model to forecast returns using price data for US and international equities and ETFs. It also demonstrates how to use Alphalens and SHAP values to assess the signal content of new features, and it contains a new appendix with over one hundred alpha factor examples.

By the end, you will be able to translate ML model predictions into a trading strategy that runs on a daily or intraday basis, as well as evaluate its performance.

What you will discover:

• Make use of market, fundamental, alternate text, and picture data.
• Using statistics, Alphalens, and SHAP values, investigate and assess alpha factors.
• Make use of machine learning approaches to tackle investment and trading issues.
• Zipline and Backtrader are used to backtest and evaluate trading techniques based on machine learning.
• Using pandas, NumPy, and pyfolio, optimize portfolio risk and performance analyses.
• Create a pairs trading strategy for US equities and ETFs based on cointegration.
• Using AlgoSeek's high-quality trades and quotations data, train a gradient boosting model to forecast intraday returns.

Machine Learning for Algorithmic Trading is for you if you are a data analyst, data scientist, Python developer, investment analyst, or portfolio manager looking to gain hands-on machine learning knowledge for trading. If you want to understand how to extract value from a varied variety of data sources using machine learning to develop your own systematic trading methods, this book is for you.

Author: Stefan Jansen

Link to buy: https://www.amazon.com/Machine-Learning-Algorithmic-Trading-alternative/dp/1839217715/

Ratings: 4.5 out of 5 stars (from 230 reviews)

Best Sellers Rank: #45,393 in Books

#13 in Computer Neural Networks

#16 in Business Investments

#16 in Artificial Intelligence (Books)