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

作　　者：蔡海尼[1] 牛冰慧 文俊浩[1] 王喜宾[2] Cai Haini;Niu Binghui;Wen Junhao;Wang Xibin(School of Software Engineering,Chongqing University,Chongqing 400044,CTdna;School of Software Engineering,Chongqing University of Posts ＆ Telecommunications,Chongqing 400065,China)

机构地区：[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

出　　处：《计算机应用研究》2018年第6期1624-1627,1659,共5页Application Research of Computers

基　　金：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(cstc2014jcyj A40054);重庆市教育委员会科学技术研究项目(KJ1600437)

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。Time series data is a high-dimensional data type in which the attributes change over time,and it reflects the dynamic 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.

关 键 词：推荐算法 概率矩阵分解 时序行为 行为预测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]