Application of BP neural network models and mind evolutionary algorithm in predicting stock composite indexes on Shanghai Stock Exchange

Stock composite indexes prediction is an important issue in the financial world. A back propagation neural network (BPNN) with mind evolutionary algorithm (MEA) developed for the prediction of prices on Shanghai Stock Exchange is presented. The optimum weights and threshold values of BPNN are determined by MEA, which solves partial minimization of BPNN. Experiments are performed with Shanghai Stock Exchange stock to determine the effectiveness of the model. The results indicate that the accuracy rate of the proposed model is more than 70%.