The commodity recommendation method for online shopping based on data mining

Abstract

With the development of E-commerce, more and more people have strong desire to buy goods on the online shopping platform. But they often need to spend more time searching for satisfactory goods because of the large amount of data. We propose a commodity recommendation model of online shopping based on data mining method in this paper. At first, we calculate the similarity between online shopping data of users’ behavior record and commodity rate, and identify the user with highest similarity as the friend of target user. Then we utilize the data of browsing history and collection commodity to analyze the recent demands of target user, and produce a demand list from the target user. After that, we search for specific commodities in friend’s shopping record according to the target user demand list, and make recommendation for the target user. Taking Taobao as the research object, we conclude that the proposed method is more accurate, and the accuracy value of our methods reached 0.315 at the condition of P@N equalling to 15 from the experiment results.