Incremental Nonnegative Matrix Factorization Based on Matrix Sketching and k-means Clustering

Along with the information increase on the Internet, there is a pressing need for online and real-time recommendation in commercial applications. This kind of recommendation attains results by combining both users' historical data and their current behaviors. Traditional recommendation algorithms have high computational complexity and thus their reactions are usually delayed when dealing with large historical data. In this paper, we investigate the essential need of online and real-time processing in modern applications. In particular, to provide users with better online experience, this paper proposes an incremental recommendation algorithm to reduce the computational complexity and reaction time. The proposed algorithm can be considered as an online version of nonnegative matrix factorization. This paper uses matrix sketching and k-means clustering to deal with cold-start users and existing users respectively and experiments show that the proposed algorithm can outperform its competitors.