Performance Comparison of Neural Networks (MLP, RBFNN, ERNN, JRNN) Models for Stock Prices Forecasting to Bank of Palestine

Abstract

This study aimed to Performance Comparison of Neural Networks (MLP, RBFNN, ERNN, JRNN) Models for the time series data of a monthly Stock Prices to Bank of Palestine from Nov. 2005 to Oct. 2020, and comparing between models to see which one is better in forecasting. The results of applying the methods were compared through the (MAPE, MAE, RMSE), the most accurate model is ERNN 14-25-1 with minimum forecast measure error.