Investigation of Various Matrix Factorization Methods for Large Recommender Systems
Investigation of Various Matrix Factorization Methods for Large Recommender Systems
复制标题
DOI：
10.1145/1722149.1722155
复制
发表时间：
2008-08
期刊：
影响因子：
--
通讯作者：
G. Takács;I. Pilászy;B. Németh;D. Tikk
中科院分区：
文献类型：
--
作者：
G. Takács;I. Pilászy;B. Németh;D. Tikk
基于矩阵分解(MF)的方法已被证明是基于评级的推荐系统的有效方法。在这项工作中，我们提出了几种提高预测精度的矩阵分解方法。我们介绍了一种新的快速(半)正的MF方法，该方法通过对用户或项目使用正值来逼近特征。我们描述了一种基于动量的MF方法。还介绍了一种导向型MF，它使用来自测试实例的信息(即用户对某些项目的评分)来提高预测精度。我们描述了一个MF的增量变体，它可以有效地处理新用户/评分，这在现实生活中的推荐系统中至关重要。在Netflix奖数据集上对提出的方法进行了测试，结果表明，该方法可以获得非常好的Quiz RMSE(最佳单项方法：0.8904，组合：0.8841)和运行时间。
Matrix factorization (MF) based approaches have proven to be efficient for rating-based recommendation systems. In this work, we propose several matrix factorization approaches with improved prediction accuracy. We introduce a novel and fast (semi)-positive MF approach that approximates the features by using positive values for either users or items. We describe a momentum-based MF approach. A transductive version of MF is also introduced, which uses information from test instances (namely the ratings users have given for certain items) to improve prediction accuracy. We describe an incremental variant of MF that efficiently handles new users/ratings, which is crucial in a real-life recommender system. A hybrid MF--neighbor-based method is also discussed that further improves the performance of MF.The proposed methods are evaluated on the Netflix Prize dataset, and we show that they can achieve very favorable Quiz RMSE (best single method: 0.8904, combination: 0.8841) and running time.