Predicting mutual fund performance using artificial neural networks

This study utilizes an artificial neural network (ANN) approach to predict the performance of equity mutual funds that follow value, blend and growth investment styles. Using a multi-layer perceptron model and GRG2 nonlinear optimizer, fund-specific historical operating characteristics were used to forecast mutual funds' risk-adjusted return. Results show that ANN generate s' better forecasting results than linear models for funds of all styles. I n addition, our model outperforms that of Chiang et al. [Chiang WC, Urban T L, Baldridge GW. A neural network approach to mutual fund net asset value f orecasting. Omega Int J Manage Sci 1996:24;205-215.] in predicting the perf ormance of growth funds. We also employed a heuristic approach of variable selection via neural networks and compared it with the stepwise selection m ethod of linear regression. Results are encouraging in that the reduced ANN models still outperform the linear models for growth and blend funds and y ield similar results for value funds. (C) 1999 Elsevier Science Ltd. All ri ghts reserved.