计算机与数字工程2017，Vol.45Issue(10)：1903-1906,1918,5.DOI:10.3969/j.issn.1672-9722.2017.10.003
基于信息熵与Mahout的推荐算法的研究
Research on Recommendation Algorithm Based on Information Entropy and Mahout
摘要
Abstract
Aiming at the noise data problem in recommendation algorithm offered by Mahout,the user entropy model is put for-ward.The user entropy model combines the concept of entropy in the information theory and uses the information entropy to measure the content of user information,which filters the noise data by calculating the entropy of users and getting rid of the users with low entropy.The proposed model is validated by using Mahout algorithm including user based collaborative filtering,collaborative filter-ing based on articles and Slope-One recommendation algorithm.The experimental results show that the proposed model can effec-tively filter out noise data,and the mean absolute error hava been decreased.关键词
噪音数据/信息熵模型/Mahout/推荐算法Key words
noisedata/information entropy model/Mahout/recommendation分类
信息技术与安全科学引用本文复制引用
樊利,林满山..基于信息熵与Mahout的推荐算法的研究[J].计算机与数字工程,2017,45(10):1903-1906,1918,5.
