An Improved OIF Elman Neural Network and Its Applications to Stock Market
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.
KeywordsStock Exchange Composite Index Stock Index Absolute Average Error Ultrasonic Motor
Unable to display preview. Download preview PDF.
- 2.Liu, X.Y., He, J.F.: Stock market prediction based on neural networks. Acta Scientiarum Naturalium Universitatis Nankaiensis 31, 39–44 (1998)Google Scholar
- 4.Yao, J.T., Tan, C.L.: Time dependent Directional Profit Model for Financial Time Series Forecasting[A]. In: International Joint Conference on Neural Networks 2000, Como Italy, pp. 291–296. IEEE Computer Society, Los Alamitos, Calif (2000)Google Scholar
- 6.Refenes, A.N., Brntz, Y., Bunn, D.W., Burgess, A.N., Zapranis, A.D.: Financial time series modeling with discounted least squares back propagation. Neural Computing 14, 123–138 (1997)Google Scholar