The CPI Forecast Based on GA-SVM

摘要：

The condition of CPI is very complex. The traditional forecast method certain limits because of the difficulty in modeling. The use of genetic algorithm optimization to improve the parameters of vector machine can avoid the blindness caused by men in selecting parameters, thus solving the problem produced by traditional and uncertain methods and promoting the training speed and the ability to predict and popularize of the model. On the basis of existed research and the analysis of the property of the parameters of the support vector machine SVM, this paper adopts genetic algorithms optimizes the parameter in SVM, then establishes the CPI forecast model based on genetic algorithms-support vector machine GA-SVM. Lastly, this paper does example forecasting by adopting this method. By doing so, the forecasting of CPI is greatly simplified. The effectiveness of the method is proved through the comparison of forecast results and actual ones.

关键词： GASVM CPI forecast model optimizeparameter the analysis of the property

作者: Feihu Qin Tianran Ma Jiehao Wang Haonan Liang Tian Zhang Huan Zhang

作者单位: School of Mechanics and Civil Engineering China University of Mining and Technology Xuzhou,China School of Science China University of Mining and Technology Xuzhou,China School of Geophysics China University of Mining and Technology Xuzhou,China

会议类型: 国际会议

会议名称: 2010 International Conference on Information,Networking and Automation(2010 IEEE信息网络与自动化国际会议 ICINA 2010)

会议地点: 昆明

会议语种:英文

页码: 142-147

在线出版日期: 2010-10-17（万方平台首次上网日期，不代表论文的发表时间）