基于Web日志挖掘的个性化推荐模型的研究

Research on Personalized Recommendation Model Based on Web Log Mining

随着电子商务系统内商品种类急剧增加,如何针对用户进行有效的个性化商品推荐成为当前的研究热点。为解决该问题,本文提出了一种基于Web日志挖掘个性化推荐模型,该模型首先利用数据预处理技术对Web日志记录进行有效的清洗和识别,随后基于MapReduce模型实现了协同过滤推荐算法的并行化,从而实现商品的快速个性化推荐。实际应用结果表明该模型提高了个性化推荐结果的准确性,具有一定的应用价值。

With the rapid increase of goods in the electronic commerce system,it has been a hot re- search topic that how to make effective personalized recommendation for users. In order to solve this problem,this paper proposes a personalized recommendation model based on Web log mining. The model first achieves effective cleaning and identification of Web log records by using data preprocess technical,then realizes rapid personalized commodity recommendation by using parallel collaborative filtering recommendation algorithm based on MapReduce model. The practical application results show that the proposed model improves the accuracy of the results of personalized recommendation, and has certain application value.