基于PMML的电子商务数据挖掘研究  

Research on E-commerce Data Mining Based on the PMML

作　　者：刘晓云[1] 焦亚琴 张银叶[2] 

机构地区：[1]安徽大学商学院,安徽合肥230601 [2]中国科学技术大学信息科学技术学院,安徽合肥230027

出　　处：《现代情报》2015年第8期57-60,130,共5页Journal of Modern Information

摘　　要：随着互联网技术的发展,电子商务进入了海量数据时代,从这些海量数据里挖掘出有用的模式具有非常高的商业价值。常规的数据挖掘模型会依赖于特定的数据挖掘平台,而目前的数据挖掘平台并不能做到随时随地跨平台交换数据挖掘模型。文章提出基于PMML的电子商务数据挖掘方法,只要数据挖掘平台兼容了PMML规范就可以真正做到跨台平交换数据挖掘模型。文章重点研究了PMML语言是如何表示完整数据挖掘模型,并就某电商平台挖掘潜在客户的数据进行实验并分析实验结果,从而验证了方案的有效性。With the development of Internet technology, E - commerce faces the tendency of the explosive growth of data, mining a useful model from these massive data has a very high commercial value. The tradition data mining model will depend on the specific data mining platform, at present the data mining platform can not exchange of data mining model cross platform when- ever and wherever possible, E- commerce data mining method based on PMML has been proposed in this thesis, as long as the data mining platform is compatible with the PMML specification which can truly exchange data mining model cross platform, This paper focuses on how the PMML language is to represent the complete data mining model, Verified the method by experiments with data from a business platform which is use to mine potential customer, and analyzed the experimental results, then verify the effectiveness of the proposed scheme.

关 键 词：电子商务 数据挖掘模型 PMML 跨平台 

分 类 号：F713.36[经济管理—产业经济]