E-Book, Englisch, 820 Seiten
Jansen Machine Learning for Algorithmic Trading
2. Auflage 2024
ISBN: 978-1-83921-678-7
Verlag: De Gruyter
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
Predictive models to extract signals from market and alternative data for systematic trading strategies with Python
E-Book, Englisch, 820 Seiten
ISBN: 978-1-83921-678-7
Verlag: De Gruyter
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
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.
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
Table of Contents - Machine Learning for Trading
- Market and Fundamental Data
- Alternative Data for Finance
- Financial Feature Engineering
- Portfolio Optimization and Performance Evaluation
- The Machine Learning Process
- Linear Models
- The ML4T Workflow
- Time-Series Models for Volatility Forecasts and Statistical Arbitrage
- Bayesian ML
- Random Forests
- Boosting Your Trading Strategy
- Data-Driven Risk Factors and Asset Allocation with Unsupervised Learning
- Text Data for Trading
- Topic Modeling
- Word Embeddings for Earnings Calls and SEC Filings
- Deep Learning for Trading
- CNNs for Financial Time Series and Satellite Images
- RNNs for Multivariate Time Series and Sentiment Analysis
- Autoencoders for Conditional Risk Factors and Asset Pricing
- Generative Adversarial Networks for Synthetic Time-Series Data
- Deep Reinforcement Learning
- Conclusions and Next Steps
- Appendix
Preface
If you are reading this, you are probably aware that machine learning (ML) has become a strategic capability in many industries, including the investment industry. The explosion of digital data closely related to the rise of ML is having a particularly powerful impact on investing, which already has a long history of using sophisticated models to process information. These trends are enabling novel approaches to quantitative investment and are boosting the demand for the application of data science to both discretionary and algorithmic trading strategies.
The scope of trading across asset classes is vast because it ranges from equities and government bonds to commodities and real estate. This implies that a very large range of new alternative data sources may be relevant above and beyond the market and fundamental data that used to be at the center of most analytical efforts in the past.
You also may have come across the insight that the successful application of ML or data science requires the integration of statistical knowledge, computational skills, and domain expertise at the individual or team level. In other words, it is essential to ask the right questions, identify and understand the data that may provide the answers, deploy a broad range of tools to obtain results, and interpret them in a way that leads to the right decisions.
Therefore, this book provides an integrated perspective on the application of ML to the domain of investment and trading. In this preface, we outline what you should expect, how we have organized the content to facilitate achieving our objectives, and what you need both to meet your goals and have fun in the process.
What to expect
This book aims to equip you with a strategic perspective, conceptual understanding, and practical tools to add value when applying ML to the trading and investment process. To this end, we cover ML as a key element in a process rather than a standalone exercise. Most importantly, we introduce an end-to-end ML for trading (ML4T) workflow that we apply to numerous use cases with relevant data and code examples.
The ML4T workflow starts with generating ideas and sourcing data and continues to extracting features, tuning ML models, and designing trading strategies that act on the models' predictive signals. It also includes simulating strategies on historical data using a backtesting engine and evaluating their performance.
First and foremost, the book demonstrates how you can extract signals from a diverse set of data sources and design trading strategies for different asset classes using a broad range of supervised, unsupervised, and reinforcement learning algorithms. In addition, it provides relevant mathematical and statistical background to facilitate tuning an algorithm and interpreting the results. Finally, it includes financial background to enable you to work with market and fundamental data, extract informative features, and manage the performance of a trading strategy.
The book emphasizes that investors can gain at least as much value from third-party data as other industries. As a consequence, it covers not only how to work with market and fundamental data but also how to source, evaluate, process, and model alternative data sources such as unstructured text and image data.
It should not be a surprise that this book does not provide investment advice or ready-made trading algorithms. On the contrary, it intends to communicate that ML faces many additional challenges in the trading domain, ranging from lower signal content to shorter time series that often make it harder to achieve robust results. In fact, we have included several examples that do not yield great results to avoid exaggerating the benefits of ML or understating the effort it takes to have a good idea, obtain the right data, engineer ingenious features, and design an effective strategy (with potentially attractive rewards).
Instead, you should find the book most useful as a guide to leveraging key ML algorithms to inform a trading strategy using a systematic workflow. To this end, we present a framework that guides you through the ML4T process of the following:
- Sourcing, evaluating, and combining data for any investment objective
- Designing and tuning ML models that extract predictive signals from the data
- Developing and evaluating trading strategies based on the results
After reading this book, you will be able to begin designing and evaluating your own ML-based strategies and might want to consider participating in competitions or connecting to the API of an online broker and begin trading in the real world.
What's new in the second edition
This second edition emphasizes the end-to-end ML4T workflow, reflected in a new chapter on strategy backtesting (, ), a new appendix describing over 100 different alpha factors, and many new practical applications. We have also rewritten most of the existing content for clarity and readability.
The applications now use a broader range of data sources beyond daily US equity prices, including international stocks and ETFs, as well as minute-frequency equity data to demonstrate an intraday strategy. Also, there is now broader coverage of alternative data sources, including SEC filings for sentiment analysis and return forecasts, as well as satellite images to classify land use.
Furthermore, the book replicates several applications recently published in academic papers. , , demonstrates how to apply convolutional neural networks to time series converted to image format for return predictions. , , shows how to extract risk factors conditioned on stock characteristics for asset pricing using autoencoders. , , examines how to create synthetic training data using generative adversarial networks.
All applications now use the latest available (at the time of writing) software versions, such as pandas 1.0 and TensorFlow 2.2. There is also a customized version of Zipline that makes it easy to include machine learning model predictions when designing a trading strategy.
Who should read this book
You should find the book informative if you are an analyst, data scientist, or ML engineer with an understanding of financial markets and an interest in trading strategies. You should also find value as an investment professional who aims to leverage ML to make better decisions.
If your background is in software and ML, you may be able to just skim or skip some introductory material in this area. Similarly, if your expertise is in investment, you will likely be familiar with some, or all, of the financial context that we provide for those with different backgrounds.
The book assumes that you want to continue to learn about this very dynamic area. To this end, it includes numerous end-of-chapter academic references and additional resources linked in the files for each chapter in the companion GitHub repository.
You should be comfortable using Python 3 and scientific computing libraries like NumPy, pandas, or SciPy and look forward to picking up numerous others along the way. Some experience with ML and scikit-learn would be helpful, but we briefly cover the basic workflow and reference various resources to fill gaps or dive deeper. Similarly, basic knowledge of finance and investment will make some terminology easier to follow.
What this book covers
This book provides a comprehensive introduction to how ML can add value to the design and execution of trading strategies. It is organized into four parts that cover different aspects of the data sourcing and strategy development process, as well as different solutions to various ML challenges.
Part 1 – Data, alpha factors, and portfolios
The first part covers fundamental aspects relevant across trading strategies that leverage machine learning. It focuses on the data that drives the ML algorithms and strategies discussed in this book, outlines how you can engineer features that capture the data's signal content, and explains how to optimize and evaluate the performance of a portfolio.
, , summarizes how and why ML became important for trading, describes the investment process, and outlines how ML can add value.
, , covers how to source and work with market data, including exchange-provided tick data, and reported financials. It also demonstrates access to numerous open source data providers that we will rely on throughout this book.
, , explains categories and criteria to assess the exploding number of sources and providers. It also demonstrates how to create alternative datasets by scraping websites, for example, to collect earnings call transcripts for use with natural language processing (NLP) and sentiment...
