Immune clustering-based recommendation algorithm

The recommender systems encounter a series of challenges as E-commerce widens its scale and scope. This paper explores the current E-commerce recommender algorithms and proposes a personalized recommender approach based on immune learning, clonal selection and self-adaption of natural immune system. Our approach first clusters initialized antibody of immune network. Then it applies self-adaptive aiNet algorithm on cluster centers for clonal variation. Compared to collaborative filtering, our approach provides more accuracy prediction on users' interest and improves the quality of recommender systems. Our experiment verifies its effectiveness and feasibility in real recommender systems.