Leverage machine learning to design and back-test automated trading strategies for real-world markets using pandas, TA-Lib, scikit-learn, LightGBM, SpaCy, Gensim, TensorFlow 2, Zipline, backtrader, Alphalens, and pyfolio.

Key Features

•  Design, train, and evaluate machine learning algorithms that underpin automated trading strategies

•  Create a research and strategy development process to apply predictive modeling to trading decisions

•  Leverage NLP and deep learning to extract tradeable signals from market and alternative data

Book Description

The explosive growth of digital data has boosted the demand for expertise in trading strategies that use machine learning (ML). This revised and expanded second edition enables you to build and evaluate sophisticated supervised, unsupervised, and reinforcement learning models.

This book introduces end-to-end machine learning for the trading workflow, from the idea and feature engineering to model optimization, strategy design, and backtesting. It illustrates this by using examples ranging from linear models and tree-based ensembles to deep-learning techniques from cutting edge research.

This edition shows how to work with market, fundamental, and alternative data, such as tick data, minute and daily bars, SEC filings, earnings call transcripts, financial news, or satellite images to generate tradeable signals. It illustrates how to engineer financial features or alpha factors that enable an ML model to predict returns from price data for US and international stocks and ETFs. It also shows how to assess the signal content of new features using Alphalens and SHAP values and includes a new appendix with over one hundred alpha factor examples.

By the end, you will be proficient in translating ML model predictions into a trading strategy that operates at daily or intraday horizons, and in evaluating its performance.

What you will learn

•  Leverage market, fundamental, and alternative text and image data

•  Research and evaluate alpha factors using statistics, Alphalens, and SHAP values

•  Implement machine learning techniques to solve investment and trading problems

•  Backtest and evaluate trading strategies based on machine learning using Zipline and Backtrader

•  Optimize portfolio risk and performance analysis using pandas, NumPy, and pyfolio

•  Create a pairs trading strategy based on cointegration for US equities and ETFs

•  Train a gradient boosting model to predict intraday returns using AlgoSeek's high-quality trades and quotes data

Table of Contents

Chapter 1: Machine Learning for Trading - From Idea to Execution

Chapter 2: Market and Fundamental Data - Sources and Techniques

Chapter 3: Alternative Data for Finance - Categories and Use Cases

Chapter 4: Financial Feature Engineering - How to Research Alpha Factors

Chapter 5: Portfolio Optimization and Performance Evaluation

Chapter 6: The Machine Learning Process

Chapter 7: Linear Models - From Risk Factors to Return Forecasts

Chapter 8: The ML4T Workflow - From ML Model to Strategy Backtest

Chapter 9: Time-Series Models for Volatility Forecasts and Statistical Arbitrage

Chapter 10: Bayesian ML - Dynamic Sharpe Ratios and Pairs Trading

Chapter 11: Random Forests - A Long-Short Strategy for Japanese Stocks

Chapter 12: Boosting Your Trading Strategy

Chapter 13: Data-Driven Risk Factors and Asset Allocation with Unsupervised Learning

Chapter 14: Text Data for Trading - Sentiment Analysis

Chapter 15: Topic Modeling - Summarizing Financial News

Chapter 16: Word Embeddings for Earnings Calls and SEC Filings

Chapter 17: Deep Learning for Trading

Chapter 18: CNNs for Financial Time Series and Satellite Images

Chapter 19: RNNs for Multivariate Time Series and Sentiment Analysis

Chapter 20: Autoencoders for Conditional Risk Factors and Asset Pricing

Chapter 21: Generative Adversarial Nets for Synthetic Time-Series Data

Chapter 22: Deep Reinforcement Learning - Building a Trading Agent

Chapter 23: Conclusions and Next Steps

Who this book is for

If you are a data analyst, data scientist, Python developer, investment analyst, or portfolio manager interested in getting hands-on machine learning knowledge for trading, this book is for you. This book is for you if you want to learn how to extract value from a diverse set of data sources using machine learning to design your own systematic trading strategies. 

Some understanding of Python and machine learning techniques is required.Table of Contents1. Machine Learning for Trading - From Idea to Execution2. Market and Fundamental Data - Sources and Techniques3. Alternative Data for Finance - Categories and Use Cases4. Financial Feature Engineering - How to Research Alpha Factors5. Portfolio Optimization and Performance Evaluation6. The Machine Learning Process7. Linear Models - From Risk Factors to Return Forecasts8. The ML4T Workflow - From Model to Strategy Backtesting(N.B. Please use the Look Inside option to see further chapters)

What's new in this second edition of Machine Learning for Algorithmic Trading?

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.

What are the key takeaways from your book?

Using machine learning for trading poses several unique challenges: first, fierce competition due to potentially high rewards in highly efficient market limits the predictive signal in historical market data. Therefore, data becomes the single most important ingredient for a predictive model and requires careful sourcing and handling. In addition, domain expertise is key to realizing the value contained in data through smart feature engineering while avoiding some of the pitfalls of using ML. 

Furthermore, ML for trading requires a workflow that integrates predictive modeling with decision making. Many books on ML show how to make good predictions, but to succeed in trading we need to translate predictions into a profitable strategy of buying and selling assets. While we should always keep the ultimate use case of an ML application in mind during development, the opportunities and methodological challenges of backtesting are fairly unique to the trading domain. 

How does Machine Learning for Algorithmic Trading differ from other algo trading books?

Compared to more generic ML books, not that many recent alternatives focus on both ML and trading. This book is perhaps the most comprehensive introduction because it covers both financial and ML fundamentals but also replicates recent research applications published by top hedge funds like AQR or at leading ML conferences like NeurIPS. 

It is not only quite long with more than 800 pages, but also includes many resources for further study. There are over 150 notebooks that illustrate ML techniques from data sourcing and model development to strategy backtesting and evaluation. In addition, the book lists numerous references and resources so that readers can build on this material to build their own ML for trading practice. 

Finally, it covers alternative data sources beyond market and fundamental data. There are three chapters on text data that show for example how to use SEC filings to predict earnings surprises with deep learning, and the book also covers working with image data.

Review

"Algorithmic Trading is about timing the market using data and algorithms in order to improve your own trading performance, outcomes, and earnings. The wealth of techniques, algorithms, and models that are used for those purposes are presented comprehensively in this giant book and are also applicable to countless other predictive modeling applications and diverse use cases. That makes this an excellent machine learning book for all learners and users of predictive algorithms in data science and analytics."

--

Dr Kirk Borne, Principal Data Scientist, Data Science Fellow, and Executive Advisor at Booz Allen Hamilton, and co-author of Ten Signs of Data Science Maturity

"Stock markets are one of the most uncertain sectors, where decision making is often more an art than a science. Machine Learning is one of the best resources to analyze a large amount of data and make the most reasonable predictions. In his book, Stefan Jansen describes all cutting-edge methods, starting from the basic concepts concerning the dynamics of a stock market and going deeper and deeper into the application of robust algorithms to implement predictive analytics. With a clear, concise, and effective style, the author guides the reader on a journey to discover time-series analysis, regression methods, Bayesian algorithms, NLP, and GANs. All algorithms are provided with financial explanations and practical examples to help the reader start making rational and intelligent investments!"

--

Giuseppe Bonaccorso, Global Head of Innovative Data Science at Bayer Pharmaceuticals, and author of Mastering Machine Learning Algorithms Second Edition

"If you have done a finance module before, you will know that data and mathematics comes together very well in the world of trading. This idea is further reinforced in the book "The Man who Solved the Market" by Gregory Zuckerman. As the world of data grows in the 4 Vs dimension, namely Volume, Variety, Velocity, and Veracity, the circumstances present many opportunities for data to be used in algorithmic trading. Stefan covers the topic of algorithmic trading comprehensively, from selecting features and portfolio management to using text mining to spot trading opportunities. You will be able to find lots of possible use cases for Machine Learning in your trading! Together with the tools stated in the book which are open-source (no license fees!), your entry into the algorithmic trading world will be easier."

--

Koo Ping Shung, Co-founder & Practicum Director at Data Science Rex, Co-founder of DataScience SG, and LinkedIn Top Voice 2020

About the Author

Stefan is the founder and CEO of Applied AI. He advises Fortune 500 companies, investment firms, and startups across industries on data & AI strategy, building data science teams, and developing end-to-end machine learning solutions for a broad range of business problems.

Before his current venture, he was a partner and managing director at an international investment firm, where he built the predictive analytics and investment research practice. He was also a senior executive at a global fintech company with operations in 15 markets, advised Central Banks in emerging markets, and consulted for the World Bank.

He holds Master's degrees in Computer Science from Georgia Tech and in Economics from Harvard and Free University Berlin, and a CFA Charter. He has worked in six languages across Europe, Asia, and the Americas and taught data science at Datacamp and General Assembly.