SVD Feature: A Toolkit for Feature-based Collaborative Filtering
In this paper we introduce SVDFeature, a machine learning toolkit for feature-based collaborative
filtering. SVDFeature is designed to efficiently solve the feature-based matrix factorization. The
feature-based setting allows us to build factorization models incorporating side information such as
temporal dynamics, neighborhood relationship, and hierarchical information. The toolkit is capable
of both rate prediction and collaborative ranking, and is carefully designed for efficient training on
large-scale data set. Using this toolkit, we built solutions to win KDD Cup for two consecutive
years.
Recommender system, which recommends items based on users’ interests, has become more and
more popular in many real-world situations. Collaborative filtering (CF) techniques, as the main
thrust behind recommender systems, have been developed for many years and keep to be a hot area
in both academia and industry. In this paper, we focus on building collaborative filtering based
recommendation toolkit which can effectively leverage the rich information of data collected and
naturally scale up to very large data set