基于混沌果蝇支持向量机回归的产品销售预测  

Product sales forecasting based on Chaos Fruit Fly Support Vector Regression

作　　者：王大溪[1] 胡志远[1] 钱柳坚 

机构地区：[1]广西科技大学电气与信息工程学院,广西柳州545006 [2]甲骨文股份有限公司软件开发部

出　　处：《计算机工程与应用》2015年第12期235-240,254,共7页Computer Engineering and Applications

基　　金：国家十二五科技支撑计划(No.2012BAF12B18);广西科技开发计划资助项目(No.桂科攻1348014-2);广西科学技术与开发计划项目(No.桂科攻0815003-1)

摘　　要：针对制造业产品销售时序具有多维、小样本、非线性、多峰等特征,提出一种混沌果蝇支持向量机回归的产品销售预测方法。将混沌理论引入到果蝇优化算法中,从而提高果蝇种群多样性和搜索的遍历性,并在寻优过程中加入混沌扰动,避免搜索过程陷入局部最优,增加持续搜索可行解的能力。并用算例验证了混沌果蝇优化算法(Chaos Fruit Fly Optimization Algorithm,CFOA)的优化性能,通过优化支持向量机回归(Support Vector Regression,SVR)的参数构建销售预测模型,进行了汽车零部件销售预测。结果表明基于混沌果蝇支持向量机回归的产品销售预测方法是有效可行的。Aiming at the product sale time series of manufacturing enterprise with multi-dimension, small samples, nonlin-earity, multi-peak, etc., a product sale forecasting method based on the chaotic fruit fly support vector regression is presented. Chaos mapping theory is combined with fruit fly optimization algorithm, thereby increasing fruit fly population diversity and search ergodicity, and chaos perturbation is added in the optimization process, which avoids the search being trapped in local optimum and increases the ability to search for feasible solutions. This paper verifies optimal performance of Chaos Fruit Fly Optimization Algorithm（CFOA）by examples, then applies CFOA to optimize parameters of Support Vector Regression（SVR）, and builds sales forecasting model. The results of application show this model in sales prediction of auto parts is effective and feasible.

关 键 词：支持向量机回归 混沌 果蝇算法 参数优化 销售预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]