Stock Index Prediction Based on Adaptive Training and Pruning Algorithm
A tapped delay neural network (TDNN) with an adaptive learning and pruning algorithm is proposed to predict the nonlinear time serial stock indexes. The TDNN is trained by the recursive least square (RLS) in which the learning-rate parameter can be chosen automatically. This results in the network converging fast. Subsequently the architecture of the trained neural network is optimized by utilizing pruning algorithm to reduce the computational complexity and enhance the network’s generalization. And then the optimized network is retrained so that it has optimum parameters. At last the test samples are predicted by the ultimate network. The simulation and comparison show that this optimized neuron network model can not only reduce the calculating complexity greatly, but also improve the prediction precision. In our simulation, the computational complexity is reduced to 0.0556 and mean square error of test samples reaches 8.7961×10− 5.
KeywordsHide Layer Input Layer Stock Index Recursive Less Square Kernel Principal Component Analysis
Unable to display preview. Download preview PDF.
- 1.Refenes, A.N., Zapranis, A., Francies, G.: Stock Performance Modeling using Neural Networks: A Comparative Study with Regression Models. Neural Network 5, 961–970 (1994)Google Scholar
- 2.Chang, B.R., Tsai, S.F.: A Grey-Cumulative LMS Hybrid Predictor with Neural Network based Weighting for Forecasting Non-Periodic Short-Term Time Series. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 6, p. 5 (2002)Google Scholar
- 5.Ince, H., Trafal, I.: Kernel Principal Component Analysis and Support Vector Machines for Stock Price Prediction. In: IEEE International Joint Conference on Neural Networks Proceedings, vol. 3, pp. 2053–2058 (2004)Google Scholar
- 7.Lecun, Y., Denker, J.S., Solla, S.A.: Optimal Brain Damage. Advances in Neural Information Processing 2, 598–605 (1989)Google Scholar
- 8.Chen, S., Chang, S.J., Yuan, J.H.: Adaptive Training and Pruning for Neural Networks Algorithms and Application. Acta Physica Sinica 50, 674–681 (2001)Google Scholar