摘要
针对基于内存的协同过滤算法在线计算量较大,数据稀疏且可扩展性较低的缺点,本文提出了一种基于SVD矩阵填充技术的K-means聚类协同过滤算法。本算法首先利用SVD降维方法对原始的高维稀疏矩阵进行预测填充,得到一个没有缺失值的评分矩阵,而后利用K-means聚类在填充完整的数据上对用户进行聚类,从而对完成对测试集上未知评分进行预测。该算法利用用户与项目之间的潜在关系克服了稀疏性问题,同时保留了聚类方法可离线建模、可扩展性好等优点。实验结果表明,该算法获得了更好的预测性能,同时具有良好的可扩展性。
Memory-based CF algorithms have the weakness of low real-time ability, data sparse and sealability. For these issues, a SVD-based K-means clustering CF algorithm is proposed. We first fill the missing ratings by SVD prediction, and then implement k-means clustering in the filled matix. This algorithm overcomes the data sparsity issue via SVD and keep the advantage of clustering, such as good real-time ability and scalability. Experiments results show that this algorithm has better forecasting performance, and has good expansibility.
出处
《微计算机信息》
2012年第8期139-141,共3页
Control & Automation
