Research on e-Commerce User Behavior Analysis Based on Big Data Collaborative Recommendation Algorithm

With the rapid development of Internet, users tend to purchase their favorite products through Internet transactions and online payment. The general trend of e-commerce development in China is that physical trading places are gradually replaced by online trading platforms on the Internet. In this paper, the restricted Boltzmann machine based on category conditions is used to describe the user's own interest preference by using the objective label of the project itself. In this process, only the project information that the user has scored is used, which strengthens the user's personalized needs. The method fully mines user behavior information, replaces commodity content big data with user behavior information as a recommended data set, and can actively push commodity content that users may be interested in to users. Experimental results show that the accuracy of RBM ( Restricted Boltzmann machine) model with nearest neighbor is higher than that of the original model, and the anti-over-fitting ability of the model is also improved.