基于用户群体兴趣变化的个性化推荐算法研究  

Personalized Recommendation AlgorithmBased on User Group Interest Change

作　　者：徐健雄 何先波[1] 何清玉 XU Jian-xiong;HE Xian-bo;HE Qing-yu(School of Computer Science,China West Normal University,Nanchong Sichuan 637009,China;School of Geographical Sciences,China West Normal University,Nanchong Sichuan 637009,China)

机构地区：[1]西华师范大学计算机学院,四川南充637009 [2]西华师范大学地理科学学院,四川南充637009

出　　处：《西华师范大学学报（自然科学版）》2022年第1期102-107,共6页Journal of China West Normal University(Natural Sciences)

基　　金：西华师范大学英才科研基金项目(17YC149)。

摘　　要：对于推荐系统,用户的喜好与用户群体的喜好存在巨大的关联。用户群体的喜好会随着时间不断变化,为了捕捉用户群体喜好变化,实现用户个性化推荐,本文提出了一种基于用户群体兴趣变化的个性化推荐算法。算法利用马尔科夫链、K均值聚类和多层神经网络的方法来捕捉用户群体的兴趣变化特征。经过在MovieLens数据集上进行的实验结果表明,本文提出的算法在多个评价指标上优于对比算法。There is a huge correlation between the user's interests and the user group s interests in the recommendation system.As the user group s interests will change over time,this paper proposes a personalized recommendation algorithm based on user group s interests change to capture the changes and realize user personalized recommendation.Markov chains,K-means clustering and multi-layer neural networks are employed to capture the interest variation features of the user group.The experimental results on MovieLens data set demonstrates that the algorithm proposed in this paper is superior to the comparison algorithm in terms of multiple evaluation indicators.

关 键 词：深度学习 神经网络 马尔科夫链 K均值聚类 推荐系统 

分 类 号：G305[文化科学] TP301.6[自动化与计算机技术—计算机系统结构]