Abstract: For the problem that the traditional Collaborative Filtering（CF） algorithms appear lower precision after clustering，a novel algorithm is proposed which employs the idiotypic immune networks to improve the CF based on user clustering. With the mechanism of artificial immune network dynamically adjusting the consistency of antibodies as well as the neighbor numbers，the algorithm makes the immune network stable，which ensures the system’s diversity，and also increases its accuracy. Simulation results show that the presented algorithm can improve the performance of CF systems in both the recommendation quality and efficiency.