Abstract
In recent years, we have entered an era of the great explosion of knowledge, how to quickly find useful information in massive data is of great importance. Therefore, in this paper, we focus on the problem of personalized rural landscape browsing recommendation. Firstly, we construct a rural landscape spot rating matrix, in which each row represents a user, and each column refers to a tourist spot. In addition, we suppose that if two users provide similar ratings on tourist spots, they may have similar interest. We use SVD smooth to convert an original sparse user/item rating matrix to a complete user/item rating matrix, and then utilize K-means to cluster users. Then, the target user is determined its category, and then its rating score can be predicted. Finally, experimental results demonstrate that the proposed algorithm can achieve lower MAE value than traditional collaborative filtering.