Improved Principal Component Analysis and Neural Network Ensemble Based Economic Forecasting
The application of neural network ensemble (NNE) to economic forecasting can heighten the generalization ability of learning systems through training multiple neural networks and combining their results. An improved principal component analysis (IPCA) is developed to extract the principal component of the economic data under the prerequisite that the main information of original economic data is not lost, and the input nodes of forecasting model are effectively reduced. Based on Bagging, the NNE constituted by five BP neural networks is employed to forecast GDP of Jiangmen, Guangdong with favorable results obtained, which shows that NNE is generally superior to simplex neural network, and valid and feasible for economic forecasting.
Unable to display preview. Download preview PDF.
- 3.Ding, L.Q., Yang, J.Q., Long, C.Y.: A Forecast Method of Generator’s Load Based on BP Artificial Neural Networks. In: Proceedings of 2005 International Conference on Management & Engineering (12th) Harbin, pp. 2319–2322 (2005)Google Scholar
- 5.Shen, X.H., Zhou, Z.H., Wu, J.X., Chen, Z.Q.: Survey of Boosting and Bagging. Computer Engineering and Application 12, 31–32 (2000)Google Scholar
- 6.Cui, Y.Q., Li, Z.B.: Application of an Improved Artificial Neural Network in Battlefield Ammunition Consumption Prediction. In: Proceedings of 2005 International Conference on Management & Engineering (12th) Harbin, pp. 182–186 (2005)Google Scholar
- 7.Cheng, Q.Y., Wang, Y.Y., Chen, W.G.: Modified Principal Component Analysis Based on Short-Term Load Forecasting. Power System Technology 29(3), 64–67 (2005)Google Scholar