Description
Book SynopsisMachine learning (ML) is progressively reshaping the fields of quantitative finance and algorithmic trading. ML tools are increasingly adopted by hedge funds and asset managers, notably for alpha signal generation and stocks selection. The technicality of the subject can make it hard for non-specialists to join the bandwagon, as the jargon and coding requirements may seem out-of-reach. Machine learning for factor investing: Python version bridges this gap. It provides a comprehensive tour of modern ML-based investment strategies that rely on firm characteristics.
The book covers a wide array of subjects which range from economic rationales to rigorous portfolio back-testing and encompass both data processing and model interpretability. Common supervised learning algorithms such as tree models and neural networks are explained in the context of style investing and the reader can also dig into more complex techniques like autoencoder asset returns, Bayesian additiv
Trade Review
"Machine learning is considered promising for investment management applications, yet the associated low signal to noise ratio presents a high bar for improving on the incumbent quant asset management tooling. The book of Coqueret and Guida is a treat for those who do not want to lose sight of the machine learning forest for the trees. Whether you are an academic scholar or a finance practitioner, you will learn just what you need to rigorously investigate machine learning techniques for factor investing applications, along with plenty of useful code snippets."
-Harald Lohre, Executive Director of Research at Robeco and Honorary Researcher at Lancaster University Management School
"Written by two experts on quantitative finance, this book covers everything from basic materials to advanced techniques in the field of quantitative investment strategies: data processing, alpha signal generation, portfolio optimization, backtesting and performance evaluation. Concrete examples related to asset management problems illustrate each machine learning technique, such as neural network, lasso regression, autoencoder or reinforcement learning. With more than 20 coding exercises and solutions provided in Python, this publication is a must for both students, academics and professionals who are looking for an up-to-date technical exposition on quantitative asset management from basic smart beta portfolios to enhanced alpha strategies including factor investing."
-Thierry Roncalli, Head of Quantitative Portfolio Strategy at Amundi Institute, Amundi Asset Management
Table of ContentsPart 1. Introduction 1. Notations and data 2. Introduction 3. Factor investing and asset pricing anomalies 4. Data preprocessing Part 2. Common supervised algorithms 5. Penalized regressions and sparse hedging for minimum variance portfolios 6. Tree-based methods 7. Neural networks 8. Support vector machines 9. Bayesian methods Part 3. From predictions to portfolios 10. Validating and tuning 11. Ensemble models 12. Portfolio backtesting Part 4. Further important topics 13. Interpretability 14. Two key concepts: causality and non-stationarity 15. Unsupervised learning 16. Reinforcement learning Part 5. Appendix 17. Data description 18. Solutions to exercises
