论文信息 - A SOM network group for DOMM financial prediction system

A SOM network group for DOMM financial prediction system

We develop a SOM (self organization mapping) neural network group to fulfill our DOMM (Dynamic Oriented Model-AutoSelection and Model-Order-AutoSelection) financial prediction system. Our experimental results show that the SOM network group can select the best prediction model and model order in an online situation with high forecasting accuracy.

Ming Zhang | Shuxiang Xu

[1] William Remus,et al. Neural Network Models for Time Series Forecasts , 1996 .

[2] Mark J. Kamstra,et al. Forecast combining with neural networks , 1996 .

[3] Chao-Hsien Chu,et al. Neural network system for forecasting method selection , 1994, Decis. Support Syst..

[4] Chin Kuo,et al. Neural Networks vs. Conventional Methods of Forecasting , 1996 .

[5] Wilpen L. Gorr,et al. Comparative study of artificial neural network and statistical models for predicting student grade point averages , 1994 .

[6] Wilpen L. Gorr,et al. Editorial: Research prospective on neural network forecasting , 1994 .

[7] A. R. Venkatachalam,et al. A neural network approach to forecasting model selection , 1995, Inf. Manag..

[8] Marcus O'Connor,et al. Artificial neural network models for forecasting and decision making , 1994 .