This textbook covers the latest advances in machine-learning methods for asset management and asset pricing. Recent research in deep learning applied to finance shows that some of the techniques used by asset managers (usually kept confidential) result in better investments than the more standard techniques. Cutting-edge material is integrated with mainstream finance theory and statistical methods to provide a coherent narrative. Coverage includes
an original machine learning method for strategic asset allocation; the no-arbitrage theory applied to a wide portfolio of assets as well as other asset management methods, such as mean-variance, Bayesian methods, linear factor models, and strategic asset allocation; and techniques other than neural networks, such as nonlinear and linear programming, principal component analysis, reinforcement learning, dynamic programming, and clustering.
The authors use technical and nontechnical arguments to accommodate readers with different levels of mathematical preparation. Readers will find the book easy to read yet rigorous and a large number of exercises.
