Book Image

Machine Learning for Algorithmic Trading - Second Edition

By : Stefan Jansen
Book Image

Machine Learning for Algorithmic Trading - Second Edition

By: Stefan Jansen

Overview of this book

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.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning for Algorithmic Trading - Second Edition
Stefan Jansen
Jul, 2020 | 822 pages
Small book image
Python for Finance Cookbook – Second Edition
Eryk Lewinson
Dec, 2022 | 740 pages
Small book image
Python for Finance Cookbook
Eryk Lewinson
Jan, 2020 | 432 pages
Small book image
Hands-On Deep Learning for Finance
Arjun Bhandari | Luigi Troiano | Elena Mejuto Villa
Feb, 2020 | 442 pages
Table of Contents (27 chapters)
Preface
Preface
What to expect
What's new in the second edition
Who should read this book
What this book covers
To get the most out of this book
Get in touch
1
Machine Learning for Trading – From Idea to Execution
Machine Learning for Trading – From Idea to Execution
The rise of ML in the investment industry
Designing and executing an ML-driven strategy
ML for trading – strategies and use cases
Summary
Free Chapter
2
Market and Fundamental Data – Sources and Techniques
Market and Fundamental Data – Sources and Techniques
Market data reflects its environment
Working with high-frequency data
API access to market data
How to work with fundamental data
Efficient data storage with pandas
Summary
3
Alternative Data for Finance – Categories and Use Cases
Alternative Data for Finance – Categories and Use Cases
The alternative data revolution
Sources of alternative data
Criteria for evaluating alternative data
The market for alternative data
Working with alternative data
Summary
4
Financial Feature Engineering – How to Research Alpha Factors
Financial Feature Engineering – How to Research Alpha Factors
Alpha factors in practice – from data to signals
Building on decades of factor research
Engineering alpha factors that predict returns
From signals to trades – Zipline for backtests
Separating signal from noise with Alphalens
Alpha factor resources
Summary
5
Portfolio Optimization and Performance Evaluation
Portfolio Optimization and Performance Evaluation
How to measure portfolio performance
How to manage portfolio risk and return
Trading and managing portfolios with Zipline
Measuring backtest performance with pyfolio
Summary
6
The Machine Learning Process
The Machine Learning Process
How machine learning from data works
The machine learning workflow
Summary
7
Linear Models – From Risk Factors to Return Forecasts
Linear Models – From Risk Factors to Return Forecasts
From inference to prediction
The baseline model – multiple linear regression
How to run linear regression in practice
How to build a linear factor model
Regularizing linear regression using shrinkage
How to predict returns with linear regression
Linear classification
Summary
8
The ML4T Workflow – From Model to Strategy Backtesting
The ML4T Workflow – From Model to Strategy Backtesting
How to backtest an ML-driven strategy
Backtesting pitfalls and how to avoid them
How a backtesting engine works
backtrader – a flexible tool for local backtests
Zipline – scalable backtesting by Quantopian
Summary
9
Time-Series Models for Volatility Forecasts and Statistical Arbitrage
Time-Series Models for Volatility Forecasts and Statistical Arbitrage
Tools for diagnostics and feature extraction
How to diagnose and achieve stationarity
Univariate time-series models
Multivariate time-series models
Cointegration – time series with a shared trend
Statistical arbitrage with cointegration
Summary
10
Bayesian ML – Dynamic Sharpe Ratios and Pairs Trading
Bayesian ML – Dynamic Sharpe Ratios and Pairs Trading
How Bayesian machine learning works
Probabilistic programming with PyMC3
Bayesian ML for trading
Summary
11
Random Forests – A Long-Short Strategy for Japanese Stocks
Random Forests – A Long-Short Strategy for Japanese Stocks
Decision trees – learning rules from data
Random forests – making trees more reliable
Long-short signals for Japanese stocks
Summary
12
Boosting Your Trading Strategy
Boosting Your Trading Strategy
Getting started – adaptive boosting
Gradient boosting – ensembles for most tasks
Using XGBoost, LightGBM, and CatBoost
A long-short trading strategy with boosting
Boosting for an intraday strategy
Summary
13
Data-Driven Risk Factors and Asset Allocation with Unsupervised Learning
Data-Driven Risk Factors and Asset Allocation with Unsupervised Learning
Dimensionality reduction
PCA for trading
Clustering
Hierarchical clustering for optimal portfolios
Summary
14
Text Data for Trading – Sentiment Analysis
Text Data for Trading – Sentiment Analysis
ML with text data – from language to features
From text to tokens – the NLP pipeline
Counting tokens – the document-term matrix
NLP for trading
Summary
15
Topic Modeling – Summarizing Financial News
Topic Modeling – Summarizing Financial News
Learning latent topics – Goals and approaches
Probabilistic latent semantic analysis
Latent Dirichlet allocation
Modeling topics discussed in earnings calls
Topic modeling for with financial news
Summary
16
Word Embeddings for Earnings Calls and SEC Filings
Word Embeddings for Earnings Calls and SEC Filings
How word embeddings encode semantics
How to use pretrained word vectors
Custom embeddings for financial news
word2vec for trading with SEC filings
Sentiment analysis using doc2vec embeddings
New frontiers – pretrained transformer models
Summary
17
Deep Learning for Trading
Deep Learning for Trading
Deep learning – what's new and why it matters
Designing an NN
A neural network from scratch in Python
Popular deep learning libraries
Optimizing an NN for a long-short strategy
Summary
18
CNNs for Financial Time Series and Satellite Images
CNNs for Financial Time Series and Satellite Images
How CNNs learn to model grid-like data
CNNs for satellite images and object detection
CNNs for time-series data – predicting returns
Summary
19
RNNs for Multivariate Time Series and Sentiment Analysis
RNNs for Multivariate Time Series and Sentiment Analysis
How recurrent neural nets work
RNNs for time series with TensorFlow 2
RNNs for text data
Summary
20
Autoencoders for Conditional Risk Factors and Asset Pricing
Autoencoders for Conditional Risk Factors and Asset Pricing
Autoencoders for nonlinear feature extraction
Implementing autoencoders with TensorFlow 2
A conditional autoencoder for trading
Summary
21
Generative Adversarial Networks for Synthetic Time-Series Data
Generative Adversarial Networks for Synthetic Time-Series Data
Creating synthetic data with GANs
How to build a GAN using TensorFlow 2
TimeGAN for synthetic financial data
Summary
22
Deep Reinforcement Learning – Building a Trading Agent
Deep Reinforcement Learning – Building a Trading Agent
Elements of a reinforcement learning system
How to solve reinforcement learning problems
Solving dynamic programming problems
Q-learning – finding an optimal policy on the go
Deep RL for trading with the OpenAI Gym
Summary
23
Conclusions and Next Steps
Conclusions and Next Steps
Key takeaways and lessons learned
ML for trading in practice
Conclusion
24
References
References
25
Index
Index
Appendix: Alpha Factor Library
Appendix: Alpha Factor Library
Common alpha factors implemented in TA-Lib
WorldQuant's quest for formulaic alphas
Bivariate and multivariate factor evaluation

Market and Fundamental Data – Sources and Techniques

Data has always been an essential driver of trading, and traders have long made efforts to gain an advantage from access to superior information. These efforts date back at least to the rumors that the House of Rothschild benefited handsomely from bond purchases upon advance news about the British victory at Waterloo, which was carried by pigeons across the channel.

Today, investments in faster data access take the shape of the Go West consortium of leading high-frequency trading (HFT) firms that connects the Chicago Mercantile Exchange (CME) with Tokyo. The round-trip latency between the CME and the BATS (Better Alternative Trading System) exchanges in New York has dropped to close to the theoretical limit of eight milliseconds as traders compete to exploit arbitrage opportunities. At the same time, regulators and exchanges have started to introduce speed bumps that slow down trading to limit the adverse effects on competition of uneven access to information.

Traditionally, investors mostly relied on publicly available market and fundamental data. Efforts to create or acquire private datasets, for example, through proprietary surveys, were limited. Conventional strategies focus on equity fundamentals and build financial models on reported financials, possibly combined with industry or macro data to project earnings per share and stock prices. Alternatively, they leverage technical analysis to extract signals from market data using indicators computed from price and volume information.

Machine learning (ML) algorithms promise to exploit market and fundamental data more efficiently than human-defined rules and heuristics, particularly when combined with alternative data, which is the topic of the next chapter. We will illustrate how to apply ML algorithms ranging from linear models to recurrent neural networks (RNNs) to market and fundamental data and generate tradeable signals.

This chapter introduces market and fundamental data sources and explains how they reflect the environment in which they are created. The details of the trading environment matter not only for the proper interpretation of market data but also for the design and execution of your strategy and the implementation of realistic backtesting simulations.

We also illustrate how to access and work with trading and financial statement data from various sources using Python.

In particular, this chapter will cover the following topics:

  • How market data reflects the structure of the trading environment
  • Working with trade and quote data at minute frequency
  • Reconstructing an order book from tick data using Nasdaq ITCH
  • Summarizing tick data using various types of bars
  • Working with eXtensible Business Reporting Language (XBRL)-encoded electronic filings
  • Parsing and combining market and fundamental data to create a price-to-earnings (P/E) series
  • How to access various market and fundamental data sources using Python

You can find the code samples for this chapter and links to additional resources in the corresponding directory of the GitHub repository. The notebooks include color versions of the images.

Previous Section
End of Section 1
Next Section