一种自适应局部和全局融合的协同过滤算法
|
摘要
相似度计算模型是协同过滤技术的核心,相似度模型的好坏直接关系到近邻用户推荐的准确性。通过用户项目评分数据集局部相似性与全局相关性分析,提出相似性度量改进模型,而改进后模型用MovieLens100K数据集实验验证,通过均方根误差、平均绝对误差和召回率三个实验结果分析。该算法可有效地提高推荐预测评分和推荐项目的准确率。
The similarity computing model is the core of collaborative filtering technology. The similarity model is directly related to the accuracy of the recommendation of neighboring users. The similarity measure improvement model was proposed by analyzing the local similarity and global correlation in the user-item scoring data set. The improved model was validated by MovieLens100 K data set experiment. Through the analysis of the three experimental verification indicators,such as mean square root error,mean absolute error and recall rate,the proposed algorithm can effectively improve the accuracy of recommended prediction scores and items.
The similarity computing model is the core of collaborative filtering technology. The similarity model is directly related to the accuracy of the recommendation of neighboring users. The similarity measure improvement model was proposed by analyzing the local similarity and global correlation in the user-item scoring data set. The improved model was validated by MovieLens100 K data set experiment. Through the analysis of the three experimental verification indicators,such as mean square root error,mean absolute error and recall rate,the proposed algorithm can effectively improve the accuracy of recommended prediction scores and items.
引文
1李聪,梁昌勇,马丽.基于领域最近邻的协同过滤推荐算法[J].计算机研究与发展,2008,45(9):1532-1538Li Cong,Liang Changyong,Ma Li.A collaborative filtering recommendation algorithm based on domain nearest neighbor[J].Journal of Computer Research and Development,2008,45(9):1532-1538
2吕苗,金淳,韩庆平.基于情境化用户偏好的协同过滤推荐模型[J].系统工程理论与实践,2016,36(12):3244-3254Lu Miao,Jin Chun,Han Qingping.Improved collaborative filtering recommendation modelbased on contextualized user preference[J].Systems Engineering Theory&Practice,2016,36(12):3244-3254
3方耀宁,郭云飞,扈红超,等.一种基于Sigmoid函数的改进协同过滤推荐算法[J].计算机应用研究,2013,30(6):1688-1691Fang Yaoning,Guo Yunfei,Hu Hongchao,et al.Improved collaborative filtering recommender algorithm based on Sigmoid function[J].Application Research of Computers,2013,30(6):1688-1691
4 Gong S J.Employing user attribute and item attribute to enhance the collaborative filtering recommendation[J].Journal of Software,2009,4(8):883-890
5程小林,熊焰,刘青文,等.一种基于自适应局部融合参数的协同过滤方法[J].计算机工程,2014,40(1):39-44Cheng Xiaolin,Xiong Yan,Liu Qingwen,et al.A collaborative filtering method based on adaptive local fusion parameter[J].Computer Engineering,2014,40(1):39-44
6李涛,王建东,叶飞跃,等.一种基于用户聚类的协同过滤推荐算法[J].系统工程与电子技术,2007,29(7):1178-1182Li Tao,Wang Jiandong,Ye Feiyue,et al.Collaborative filtering recommendation algorithm based on clustering basal users[J].Journal of Systems Engineering and Electronics,2007,29(7):1178-1182
7胡川,孟祥武,张玉洁,等.一种改进的偏好融合组推荐方法[J].软件学报,2018,29(10):3164-3183Hu Chuan,Meng Xiangwu,Zhang Yujie,et al.Enhanced group recommendation method based on preference aggregation[J].Journal of Software,2018,29(10):3164-3183
8程芳,沈红岩,赵艳.一种有效缓解数据稀疏问题的协同过滤推荐算法[J].现代情报,2016,36(3):76-79Cheng Fang,Shen Hongyan,Zhao Yan.Collaborative filtering recommendation algorithm for alleviating data sparsity[J].Journal of Modern Information,2016,36(3):76-79
9 Zhao X,Niu Z,Chen W.Opinion based collaborative filtering to solve popularity bias in recommender systems[C]//International Conference on Database and Expert Systems Applications.Berlin,Heidelberg:Springer,2013:426-433
10 Breese J S,Heckerman D,Kadie C.Empirical analysis of predictive algorithms for collaborative filtering[J].Uncertainty in Artificial Intelligence,2013,98(7):43-52
2吕苗,金淳,韩庆平.基于情境化用户偏好的协同过滤推荐模型[J].系统工程理论与实践,2016,36(12):3244-3254Lu Miao,Jin Chun,Han Qingping.Improved collaborative filtering recommendation modelbased on contextualized user preference[J].Systems Engineering Theory&Practice,2016,36(12):3244-3254
3方耀宁,郭云飞,扈红超,等.一种基于Sigmoid函数的改进协同过滤推荐算法[J].计算机应用研究,2013,30(6):1688-1691Fang Yaoning,Guo Yunfei,Hu Hongchao,et al.Improved collaborative filtering recommender algorithm based on Sigmoid function[J].Application Research of Computers,2013,30(6):1688-1691
4 Gong S J.Employing user attribute and item attribute to enhance the collaborative filtering recommendation[J].Journal of Software,2009,4(8):883-890
5程小林,熊焰,刘青文,等.一种基于自适应局部融合参数的协同过滤方法[J].计算机工程,2014,40(1):39-44Cheng Xiaolin,Xiong Yan,Liu Qingwen,et al.A collaborative filtering method based on adaptive local fusion parameter[J].Computer Engineering,2014,40(1):39-44
6李涛,王建东,叶飞跃,等.一种基于用户聚类的协同过滤推荐算法[J].系统工程与电子技术,2007,29(7):1178-1182Li Tao,Wang Jiandong,Ye Feiyue,et al.Collaborative filtering recommendation algorithm based on clustering basal users[J].Journal of Systems Engineering and Electronics,2007,29(7):1178-1182
7胡川,孟祥武,张玉洁,等.一种改进的偏好融合组推荐方法[J].软件学报,2018,29(10):3164-3183Hu Chuan,Meng Xiangwu,Zhang Yujie,et al.Enhanced group recommendation method based on preference aggregation[J].Journal of Software,2018,29(10):3164-3183
8程芳,沈红岩,赵艳.一种有效缓解数据稀疏问题的协同过滤推荐算法[J].现代情报,2016,36(3):76-79Cheng Fang,Shen Hongyan,Zhao Yan.Collaborative filtering recommendation algorithm for alleviating data sparsity[J].Journal of Modern Information,2016,36(3):76-79
9 Zhao X,Niu Z,Chen W.Opinion based collaborative filtering to solve popularity bias in recommender systems[C]//International Conference on Database and Expert Systems Applications.Berlin,Heidelberg:Springer,2013:426-433
10 Breese J S,Heckerman D,Kadie C.Empirical analysis of predictive algorithms for collaborative filtering[J].Uncertainty in Artificial Intelligence,2013,98(7):43-52