中小企业税务稽查投影寻踪建模与实证分析  

Tax-Checking Assessment of Small and Medium-Sized Enterprises Applying Projection Pursuit Clustering Technique and Its Positive Research

作　　者：楼文高[1] 楼际通[2] 宋雷娟[1] 王浪庆[1] 

机构地区：[1]上海商学院财经学院,上海200235 [2]北卡罗来纳大学教堂山分校,nc27514

出　　处：《经济数学》2015年第4期1-6,共6页Journal of Quantitative Economics

基　　金：上海高校知识服务平台"上海商贸服务业知识服务中心"建设子项目"税收风险管理信息系统设计及开发"(ZF1226);上海地方本科院校"十二五"内涵建设上海商学院重点学科专业建设"金融学人才培养模式改革与创新";2013年国家大学生创新创业训练计划项目(CXGJ-13-002)资助

摘　　要：从上海市某区386家中小企业申报的15项税收指标数据中筛选出对判定企业纳税情况具有重要影响的10个评价指标,并将全部386个样本分成性质相似的建模样本和测试样本(其中测试样本个数占45%),建立了基于投影寻踪分类(PPC)技术的税务稽查评价模型.与多元线性回归(MLR)、判别分析(MDA)、Logistic和支持向量机(SVM)模型相比,PPC模型的识别错误率最低,建模样本和测试样本的平均分类错误率低于6%,改进型PPC模型包含的评价指标少,两类错误率很接近,非常适用于实际企业的税务稽查评估研究和实践.对339家待判断企业纳税情况的判定结果研究表明,建立的改进型PPC模型具有很好的泛化能力和鲁棒性.Based on the 15variables＇（indexes＇）tax-reporting data of 386wooden-furniture manufacturing small-and medium-sized enterprises（WFMSMEs）located in some districts of Shanghai city,the ten variables mainly influencing the taxchecking situation（tax evasion or compliance）of the 386 WFMSMEs were obtained by applying sensitivity analysis method（SAM）for selecting input variables.The modelling set data and testing set data（about taking up 45%）with similar characteristics-similar mean values and variance-were divided using self-organizing map（SOM）approach.The practical,feasible and effective projection pursuit clustering（PPC）model for tax-checking assessment was thus established.Compared with the multivariate linear regression（MLR）,the multivariate discriminant analysis（MDA）,Logistic and the support vector machine（SVM）,the established PPC model possesses the most accurate and the lowest classification-error percentage（CEP）of the models.The mean CEP of modelling set data and the testing set data is lower than 6%.The improved PPC model including fewer variables is thus suitable to tax-checking assessment and research.The tax-checking situation of the other 339 WFMEs was also assessed and judged,and the results show that the established improved PPC model possesses high generalization and robustness.

关 键 词：税务稽查 投影寻踪分类技术 分类错误率 样本分组 

分 类 号：TV139.1[水利工程—水力学及河流动力学] N945.12[自然科学总论—系统科学]