B2C模式多层购物体系时镜反转商品数据降维挖掘

Commodity Data Mining with Dimensionality Reduction of Multilayer Shopping System in B2C Mode Based on Time Reversal Mirror

提出一种B2C模式下商品数据降维挖掘处理的商品推荐及实现方法,在B2C模式多层购物体系下,采用被动时间反转镜技术建构多维商品数据的降维模型,采用数据挖掘的方法提取用户在网站上浏览信息,留言信息等,综合对信息进行数据挖掘处理,提取用户最关心的信息,然后对相应的用户推荐相应类型的商品,从而大大提高B2C模式下电子商务的交易成功率;采用一种商品在北京市的分布作为研究对象比较推荐前后的商品覆盖率,结果显示,基于数据挖掘的B2C模式下商品推荐将商品覆盖率提高了66%。研究成果展示了在电子商务管理的良好的应用前景和价值。

The browse information, message were all used, the data mining was finished with all aspects, space domain and frequency domain, due to the relationship of the same image in time, space, frequency domain, the most important information was extracted out, and the response information was shown to the user, with which, the success rate in B2C mode was improved well, A distribution of a product in Beijing was taken as target to test the ability, and the result shows that with data mining in B2C mode, the success rate in commodity recommend was improved 66% higher. Research result shows good perspective and application value in Electronic Commerce management.