基于数据挖掘的CRM决策支持系统研究

【作者】 黄伟良；

【导师】 陈杰；

【作者基本信息】 南京理工大学 ， 机械电子工程， 2004， 硕士

【摘要】 数据仓库和数据挖掘技术的快速发展，促进着企业决策支持系统的不断更新，企业决策支持系统是近年来数据挖掘技术在客户关系管理(CRM)中的又一新的应用。决策支持系统作为分析层次的CRM主体，需要理解客户特性和客户行为，利用数据挖掘工具，实现对客户群的认识、分类和评估，然后通过优化服务来实现客户获取、客户保留、客户忠诚和客户盈利的目的。 本文以徐工集团营销公司CRM开发为背景，对其中涉及的决策支持关键技术在作深入探讨和研究。主要是对当今流行的基于数据仓库的数据挖掘技术作了相关介绍，并阐述数据挖掘技术在DSS中的应用。选取决策树分类算法为研究重点。研究了SLIQ算法的预处理、计算最佳分裂、执行分裂几个大的阶段以及具体算法设计实现过程，并在随后结合该算法设计客户价值分类模型。 结合当前流行的MS．NET技术，构建了应用于该机械制造业的DSS系统解决方案。最后提供了该方案的技术实现方法，完成了系统的原型的开发。更多还原

【Abstract】 The rapid development of Data warehouse and Data mining technologies have promoted update of Decision Support System. DSS is a new application of data mining technologies in CRM(Customers Relationship Management) recently. So people Can idenify classify and evaluate the customers by understanding of the customers characteristic and behaviors in CRM with the help of data mining tools , and then fulfill the purposes of customers loyalty costomers profitability and customers retention and customers acquisition through improving Customer Services.With the background of CRM software developing of XuZhou Construction machinery Group ,the related key technologies about DSS are studied in this paper. After introducing these data mining technologies and methods based on data warehouse, the application of these technologies are expatiated in DSS. In this paper ,the decision tree classify algorithm is choosed as the emphasis.The author designed out the process of SLIQ(Supervised Learning In Quest) algorithm,which is made up of the main following step:pre-sorth best-split, update-label,then provide CRM classifies model with SLIQ algorithm in next chapter.Through utilizing Microsoft DotNet technology, DSS solution that is suitable for the mechanism manufacturing enterprise is provided, then is put into practice at last.更多还原