Collaborative Evolution for User Profiling in Recommender Systems.

Accurate user profiling is important for an online recommender system to provide proper personalized recommendations to its users. In many real-world scenarios, the user's interests towards the items may change over time. Therefore, a dynamic and evolutionary user profile is needed. In this work, we come up with a novel evolutionary view of user's profile by proposing a Collaborative Evolution (CE) model, which learns the evolution of user's profiles through the sparse historical data in recommender systems and outputs the prospective user profile of the future. To verify the effectiveness of the proposed model, we conduct experiments on a real-world dataset, which is obtained from the online shopping website of Tencent Inc.-- www.51buy.com and contains more than 1 million users' shopping records in a time span of more than 180 days. Experimental analyses demonstrate that our proposed CE model can be used to make better future recommendations compared to several state-of-the-art methods.