摘要
作为一种基于项目的协同过滤推荐算法,Slope One算法易于实现且高效。但由于Slope One算法未考虑用户相似性,导致其在处理涉及用户关系的个性化推荐任务时性能不高。针对以上问题,提出了改进的Slope One算法。提出一种均衡接近度灰关联分析方法计算用户之间的均衡接近度,利用均衡接近度度量用户间的相似程度,然后将均衡接近度值融入到Slope One算法中进行评分预测,在MovieLens和Epinions数据集下的对比实验表明,该算法具有更低的平均绝对误差(MAE)和均方根误差(RMSE),提高了预测的准确度和推荐质量。
As an item-based collaborative filtering algorithm, Slope One algorithm is not only easy to implement, but also efficient. However, the performance of the Slope One algorithm is not well when dealing with personalized recommendation tasks, which require analyzing relationships. Considering that the above problems, an improved Slope One algorithm is proposed. Firstly, this paper proposes a grey correlational analysis by the method of degree of balance approach to calculate the degree of balance between users, which measures the degree of similarity between user-pairs, and then integrates it into Slope One algorithm for rating prediction. Finally, the comparison experiments on MovieLens and Epinions datasets show that the proposed algorithm has lower Mean Absolute Error(MAE)and Root Mean Squared Error(RMSE),improves the accuracy of prediction and recommendation quality.
作者
张岐山
陈露露
ZHANG Qishan;CHEN Lulu(School of Economics and Management,Fuzhou University,Fuzhou 350108,China)
出处
《计算机工程与应用》
CSCD
北大核心
2021年第9期96-102,共7页
Computer Engineering and Applications
基金
国家自然科学基金(61300104)
福建省自然科学基金(2018J01791)。
关键词
协同过滤
均衡接近度
灰关联
Slope
One算法
用户相似度
collaborative filtering
degree of balance and approach
grey relational analysis
Slope One algorithm
user similarity
