《计算机应用研究》|Application Research of Computers

基于时序模型和矩阵分解的推荐算法

Recommender algorithm based on time series model and matrix factorization

免费全文下载 (已被下载 次)  
获取PDF全文
作者 蔡海尼,牛冰慧,文俊浩,王喜宾
机构 1.重庆大学 软件学院,重庆 400044;2.重庆邮电大学 软件工程学院,重庆 400065
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)06-1624-04
DOI 10.3969/j.issn.1001-3695.2018.06.005
摘要 时间序列数据是一种数据属性随时间变化的高维数据类型,反映了用户兴趣的动态变化。基于时序数据的推荐系统利用用户的行为时间提高推荐的准确性,但不适用于大规模数据集的推荐任务。矩阵分解方法是处理高维数据集时常用的降维方法。为此,提出一种基于时序模型和矩阵分解的推荐算法。基于该方法,首先利用矩阵分解提取原始时序数据的特征,然后通过时序模型挖掘特征的趋势,最后根据预测的特征得到预测结果并进行推荐。实验结果表明,所提出的算法与已有的推荐算法相比,在均方根误差(root mean square error,RMSE)和平均准确率(mean average precision,MAP)两个指标上均有较好表现,且适用于大规模数据的推荐任务。
关键词 推荐算法;概率矩阵分解;时序行为;行为预测
基金项目 国家自然科学基金资助项目(61672117)
重庆市自然科学基金资助项目(cstc2014jcyjA40054)
重庆市教育委员会科学技术研究项目(KJ1600437)
本文URL http://www.arocmag.com/article/01-2018-06-005.html
英文标题 Recommender algorithm based on time series model and matrix factorization
作者英文名 Cai Haini, Niu Binghui, Wen Junhao, Wang Xibin
机构英文名 1.SchoolofSoftwareEngineering,ChongqingUniversity,Chongqing400044,China;2.SchoolofSoftwareEngineering,ChongqingUniversityofPosts&Telecommunications,Chongqing400065,China
英文摘要 Time series data is a high-dimensional data type in which the attributes change over time, and it reflects the dyna-mic change of user interest.Recommender system based on the time series data is able to improve the efficiency of recommendation, but it is not suitable for large scale data sets, matrix factorization is a commonly used method to reduce the dimension of high dimensional data set.This paper proposed a method to combine the time-series model with matrix factorization.Firstly, this method extracted the characteristics of the original time series data by using the matrix factorization, then it extracted the trend of the feature by the sequential model.Finally, it obtained the prediction results according to the predicted characteristics.The experiments demonstrate that the proposed method performs better on root mean square error(RMSE) and mean average precision(MAP) than the conventional recommender algorithms, and it is also appropriate for the prediction task of large-scale data.
英文关键词 recommender algorithms; probabilistic matrix factorization(PMF); sequential behavior; behavior prediction
参考文献 查看稿件参考文献
  [1] 郑修猛, 陈福才, 柯丽虹. 基于信任和概率矩阵分解的协同推荐算法研究[J] . 计算机应用研究, 2016, 33(11):3240-3244.
[2] Sharifi Z, Rezghi M, Nasiri M. A new algorithm for solving data sparsity problem based on non negative matrix factorization in recommender systems[C] //Proc of International Conference on Computer and Knowledge Engineering. Piscataway, NJ:IEEE Press, 2014:56-61.
[3] Hu Yan, Peng Qimin, Hu Xiaohui, et al. Time aware and data sparsity tolerant Web service recommendation based on improved collaborative filtering[J] . IEEE Trans on Services Computing, 2015, 8(5):782-794.
[4] Tu Shitao, Zhu Lanjuan. A bandit method using probabilistic matrix factorization in recommendation[J] . Journal of Shanghai Jiaotong University:Science, 2015, 20(5):535-539.
[5] Song Yang, Zhuang Ziming, Li Huajing, et al. Real-time automatic tag recommendation[C] //Proc of the 31st International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2008:515-522.
[6] 王守辉, 于洪涛, 黄瑞阳, 等. 基于模体演化的时序链路预测方法[J] . 自动化学报, 2016, 42(5):735-745.
[7] Xiong Liang, Chen Xi, Huang T K, et al. Temporal collaborative filtering with Bayesian probabilistic tensor factorization[C] //Proc of SIAM International Conference on Data Mining. 2010:211-222.
[8] Salakhutdinov B R, Mnih A. Probabilistic matrix factorization[C] //Proc of the 20th International Conference on Neural Information Processing Systems. Vancouver, Canada:Curran Associates Inc. , 2015:1257-1264.
[9] Bokde D, Girase S, Mukhopadhyay D. Matrix factorization model in collaborative filtering algorithms:a survey[J] . Procedia Computer Science, 2015, 49(1):136-146.
[10] Li Gai, Ou Weihua. Pairwise probabilistic matrix factorization for implicit feedback collaborative filtering[J] . Neurocomputing, 2016, 204(9):17-25.
[11] 田尧, 秦永彬, 许道云, 等. 基于双信任机制的TrustSVD算法[J] . 计算机科学与探索, 2015, 9(11):1391-1397.
[12] 涂丹丹, 舒承椿, 余海燕. 基于联合概率矩阵分解的上下文广告推荐算法[J] . 软件学报, 2013, 24(3):454-464.
[13] Amin A, Colman A, Grunske L. An approach to forecasting QoS attributes of Web services based on ARIMA and GARCH models[C] //Proc of IEEE International Conference on Web Services. Washington DC:IEEE Computer Society, 2012:74-81.
[14] Wang Jian, Deng Wei, Guo Yuntao. New Bayesian combination method for short-term traffic flow forecasting[J] . Transportation Research Part C:Emerging Technologies, 2014, 43(6):79-94.
[15] Yu Yong, Hui C L, Choi T M. An empirical study of intelligent expert systems on forecasting of fashion color trend[J] . Expert Systems with Applications, 2012, 39(4):4383-4389.
[16] 孙光福, 吴乐, 刘淇, 等. 基于时序行为的协同过滤推荐算法[J] . 软件学报, 2013, 24(11):2721-2733.
[17] Koren Y. Collaborative filtering with temporal dynamics[C] //Proc of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2009:89-97.
[18] 章登义, 欧阳黜霏, 吴文李. 针对时间序列多步预测的聚类隐马尔可夫模型[J] . 电子学报, 2014, 42(12):2359-2364.
[19] 王守涛. 一种基于多维时间序列分析的音乐推荐系统研究与实现[D] . 南京:南京大学, 2014.
收稿日期 2017/2/14
修回日期 2017/4/9
页码 1624-1627,1659
中图分类号 TP391.9
文献标志码 A