A Recommendation System Algorithm Based on Large Scale Internet Environment

With the growing scale of the Internet, the amount of data is increasing rapidly as well. In order to improve the user experience, the recommendation system came into being. It recommends products to the user by analyzing the user's behavior. In the recommendation system, collaborative filtering algorithm is one of the most widely used algorithms. While the traditional collaborative filtering is no longer suitable for large-scale network, where the algorithm efficiency is low, as well as, it has the extremely sparse problem. To solve those problems, we designed an improved collaborative filtering algorithm for network segmentation. The algorithm uses a segmentation rules to partition the large-scale network, and decompose the problem into sub-problems. Ultimately, it can help us to meet the purpose of optimizing the algorithm.