Can machines learn Chinese mutual funds?

This study applies machine learning techniques to predict mutual fund performance and construct high-performing portfolios in the Chinese mutual fund market. Using Random Forest, XGBoost, and LightGBM models, we frame fund selection as a classification problem, estimating each fund's probability of outperforming the market benchmark. Filtered fund characteristics serve as predictors, allowing us to build investable portfolios ranked by predicted outperformance likelihood. Empirical results reveal that machine learning-based portfolios consistently outperform the benchmark, with LightGBM delivering the strongest performance across key metrics. Furthermore, a flexible machine learning combination framework is introduced to improve predictive robustness and portfolio stability. These findings highlight the practical value of machine learning for fund selection and strategy design in complex financial environments. • Utilizing machine learning techniques (Random Forest, XGBoost, LightGBM) to predict the performance of Chinese mutual funds and construct outperforming portfolios. • Formulating fund selection as a classification problem, focusing on relative outperformance rather than absolute returns, with fund characteristics filtered through statistical and machine learning-based feature selection methods. • Optimizing models using K-fold cross-validation to ensure robustness and accuracy of predictions, and constructing portfolios ranked by predicted probabilities of fund outperformance. • Empirical results show that machine learning-based portfolios consistently outperformed the market benchmark, with LightGBM achieving the best performance. • Enhancing prediction robustness and return monotonicity through a forecast combination framework, integrating outputs from multiple models. • Enriching the literature on machine learning applications in financial markets, particularly in the underexplored Chinese mutual fund market, and demonstrating the effectiveness of tree-based models in identifying outperforming funds.