Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices

ISBN-13: 9781316516195 / Angielski

Agostino Capponi; Charles-Albert Lehalle

Opis

Written by more than sixty experts in the area, this book reviews cutting-edge practices in machine learning for financial markets, and explores connections with data science and more traditional approaches. This is an invaluable resource for researchers and graduate students in financial engineering, as well as practitioners in the sector.

Recenzje

'Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices' comes at a critical time in the financial markets. The amount of machine readable data available to practitioners, the power of the statistical models they can build, and the computational power available to train them keeps growing exponentially. AI and machine learning are increasingly embedded into every aspect of the investing process. The common curriculum, however, both in finance and in applications of machine learning, lags behind. This book provides an excellent and very thorough overview of the state of the art in the field, with contributions by key researchers and practitioners. The monumental work done by the editors and reviewers shows in the wide diversity of current topics covered – from deep learning for solving partial differential equations to transformative breakthroughs in NLP. This book, which I cannot recommend highly enough, will be useful to any practitioner or student who wishes to familiarize themselves with the current state of the art and build their careers and research on a solid foundation.' Gary Kazantsev, Bloomberg and Columbia University

Spis treści

Interacting with Investors and Asset Owners: Part I. Robo-advisors and Automated Recommendation: 1. Introduction to Part I. Robo-advising as a technological platform for optimization and recommendations; 2. New frontiers of robo-advising: consumption, saving, debt management, and taxes; 3. Robo-advising: less AI and more XAI? Augmenting algorithms with humans-in-the-loop; 4. Robo-advisory: from investing principles and algorithms to future developments; 5. Recommender systems for corporate bond trading; Part II. How Learned Flows Form Prices: 6. Introduction to Part II. Price impact: information revelation or self-fulfilling prophecies?; 7. Order flow and price formation; 8. Price formation and learning in equilibrium under asymmetric information; 9. Deciphering how investors' daily flows are forming prices; Towards Better Risk Intermediation: Part III. High Frequency Finance: 10. Introduction to Part III; 11. Reinforcement learning methods in algorithmic trading; 12. Stochastic approximation applied to optimal execution: learning by trading; 13. Reinforcement learning for algorithmic trading; Part IV. Advanced Optimization Techniques: 14. Introduction to Part IV. Advanced optimization techniques for banks and asset managers; 15. Harnessing quantitative finance by data-centric methods; 16. Asset pricing and investment with big data; 17. Portfolio construction using stratified models; Part V. New Frontiers for Stochastic Control in Finance: 18. Introduction to Part V. Machine learning and applied mathematics: a game of hide-and-seek?; 19. The curse of optimality, and how to break it?; 20. Deep learning for mean field games and mean field control with applications to finance; 21. Reinforcement learning for mean field games, with applications to economics; 22. Neural networks-based algorithms for stochastic control and PDEs in finance; 23. Generative adversarial networks: some analytical perspectives; Connections with the Real Economy: Part VI. Nowcasting with Alternative Data: 24. Introduction to Part VI. Nowcasting is coming; 25. Data preselection in machine learning methods: an application to macroeconomic nowcasting with Google search data; 26. Alternative data and ML for macro nowcasting; 27. Nowcasting corporate financials and consumer baskets with alternative data; 28. NLP in finance; 29. The exploitation of recurrent satellite imaging for the fine-scale observation of human activity; Part VII. Biases and Model Risks of Data-Driven Learning: 30. Introduction to Part VII. Towards the ideal mix between data and models; 31. Generative Pricing model complexity: the case for volatility-managed portfolios; 32. Bayesian deep fundamental factor models; 33. Black-box model risk in finance; Index.