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.