Chaos Forecasting Model for GDP Based on Neural Networks Error-Correction

摘要：

To perform a simulation forecast about the increasing rate for 2004 -2006 annual GDP based on chaotic attractors,aiming at the shortcoming that chaotic time series can not fit the actual fluctuation of small sample discrete data very well,especially for long-term economic forecast errors.This paper makes use of BP neural network to predict the fitting errors above,and to correct the final results based on the prediction.The three-year average relative error rate is up to 0.553％,the prediction accuracy has been improved significantly.

关键词： Non-linear dynamics Neural networks Chaos Logistic map GDP

作者: AO Shan TANG Shoulian

作者单位: Economics and Management School,Beijing University of Posts and Telecommunications,P.R.China,100876

会议类型: 国际会议

会议名称: 2007 International Conference on Management Science and Engineering(2007管理科学与工程国际学术会议)

会议地点: 河南焦作

会议语种:英文

页码: 2705-2711

在线出版日期: 2007-08-20（万方平台首次上网日期，不代表论文的发表时间）