Fund performance evaluation with explainable artificial intelligence

We apply explainable artificial intelligence (xAI) to a large dataset of global equity funds. Our approach combines the XGBoost model with Shapley values; the former is a machine learning framework that enhances model fitness while the latter is an xAI method that provides informed explanations regarding the direction and significance of predictors. Based on macrofinance and fund-level factors, our fund performance evaluation of G10 countries uncovers novel insights into the diversification of country portfolios: both over-and under-diversification are associated with poor performance. Our analysis establishes consistency through a benchmark linear regression model and robustness at country level.