With the trend towards increasing computing resources and larger data sets, machine learning has become an important skill set for the financial sector. This book is intended for advanced graduate students and academics in financial econometrics, financial mathematics, and applied statistics, as well as quantum and data scientists in quantitative finance.

Machine Learning in Finance: From Theory to Practice is divided into three parts, each covering theory and applications. The first presents supervised learning for transversal data from a Bayesian and frequentist perspective. The more advanced material places a strong emphasis on neural networks, including deep learning, as well as Gaussian processes, with examples from investment management and derivative modeling. The second part presents supervised learning for time series data, probably the most commonly used type of data in finance, with examples from the areas of trading, stochastic volatility and bond models.

Finally, the third part presents reinforcement learning and its applications in trading, investing and wealth management. Python code examples are provided to help readers understand the methods and applications. The book also contains more than 80 math and programming exercises with elaborate solutions available to instructors. As a bridge to research in this emerging field, the final chapter presents the limitations of machine learning in finance from a researcher's perspective and shows how many well-known concepts in statistical physics could emerge as key methods of machine learning in finance.