Abstract
To improve the performance of electronic commerce recommendation system (ECRS), the system implement frame by case-based reasoning (CBR) and artificial immune system (AIS) is proposed. The inner mechanism of AIS is analyzed, in leaning subsystem of ECRS, the AIS implement cycles such as antigen identifying, initial antibody population generating, affinity calculating, clone selecting, population updating and so on are studied. The key techniques of CBR for reasoning subsystem of ECRS such as case representation, case retrieval, case adaptation and case maintenance are introduced. The ECRS is tested by history record information of some Website, the result demonstrates that both the recommendation accuracy and reasoning response velocity are improved, the ECRS frame based on CBR and AIS is a potent one.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have