Customizing knowledge-based recommender system by tracking analysis of user behavior

In this paper, we reviewed the major problems in the existing recommender systems and presented a tracking recommender approach based on user's behavior information and two-level property of items. Our proposed approach defined user profile model, knowledge resources model and constructed Formal Concept Analysis (FCA) mapping to guide a personalized recommendation for user. We simulated a prototype recommender system that can make the quality recommendation by tracking user's behavior. The experimental result showed our strategy was more robust against the drawbacks and preponderant than conventional recommender systems.