Content-based recommendation in E-commerce

Recommendation system is one of the most important techniques in some E-commerce systems such as virtual shopping mall. With the prosperity of E-commerce, more and more people are willing to perform Internet shopping, which resulted in an overwhelming array of products. Traditional similarity measure methods make the quality of recommendation system decreased dramatically in this situation. To address this issue, we present a novel method that combines the clustering which is based on apriori-knowledge and content-based technique to calculate the customer's nearest neighbor, and then provide the most appropriate products to meet his/her needs. Experimental results show efficiency of our method.