Hi-index | 0.00 |
An improved model is proposed based on the OIF Elman neural network by introducing direction and time profit factors and applied to the prediction of the composite index of stock. Simulation results show that the proposed model is feasible and effective. Comparisons are also made when the stock exchange is performed using prediction results from different models. It shows that the proposed model could improve the prediction precision evidently and realize the main purpose for investors to obtain more profits.