This book will present 12 chapters covering topics including machine learning concepts, algorithms and their applications. More specically, this book introduces methods such as kernel switching ridge regression, sentimental analysis, decision trees, and random forests. It also introduces empirical studies applying ML in multiple nance and accounting areas, such as forecasting of mortality for insurance product pricing, using kernel switching ridge regression for improving
prediction models, managing risk and nancial crimes, and predicting stock return volatilities.
Given the lack of availability of sucient books in this area, this book will be useful to researchers,
including academics and research students, who are interested in advanced machine learning tools
and their applications. e contents of this proposed book are also expected to benet practitioners who are involved in forecasting modeling, stock-trading risk management, bankruptcy
prediction, accounting and banking fraud detection, insurance product pricing, credit risk management, and portfolio management. We believe ndings from this book will add new insights
into the stream of computational nance and accounting research.