Artificial Intelligence and Machine Learning in Fund Performance Evaluation — A Review

Financial technology (Fintech) has become an emerging and powerful tool that contributes to the advancement of finance research. With the recent development of Fintech, machine-learning (ML) techniques have been continuously deployed for developing more effective models in financial research. This chapter aims to provide in-depth details of ML implementation in fund performance evaluation and prediction. Building on the theoretical basics of ML, we first introduce several widely applied ML algorithms, including linear regression, least absolute shrinkage and selection operator (LASSO), ridge, K nearest neighbors (KNN), decision trees (DT), random forest (RF), support vector machine (SVM), deep learning (DL), and artificial neural networks (ANN). We then focus on each method’s applicable conditions and how it contributes to forecasting and evaluating fund performance. The advantages of using ML methods over traditional methods in evaluating fund performance are also discussed.