Context-aware Ensemble of Multifaceted Factorization Models for Recommendation Prediction in Social Networks
This work addresses recommendation accuracy in social networks, but it is incremental as it builds on existing factorization methods with additional features and ensemble techniques.
The paper tackled recommendation prediction in social networks by proposing a multifaceted factorization model that integrates social relationships, user actions, and various features like keywords and time, achieving second place in the KDD-Cup 2012 with scores of 0.43959 (public) and 0.41874 (private).
This paper describes the solution of Shanda Innovations team to Task 1 of KDD-Cup 2012. A novel approach called Multifaceted Factorization Models is proposed to incorporate a great variety of features in social networks. Social relationships and actions between users are integrated as implicit feedbacks to improve the recommendation accuracy. Keywords, tags, profiles, time and some other features are also utilized for modeling user interests. In addition, user behaviors are modeled from the durations of recommendation records. A context-aware ensemble framework is then applied to combine multiple predictors and produce final recommendation results. The proposed approach obtained 0.43959 (public score) / 0.41874 (private score) on the testing dataset, which achieved the 2nd place in the KDD-Cup competition.