Collaborative Recommendation for Scenic Spots Based on Distance

In the collaborative filtering recommendation algorithm, the similarity calculation plays an important role in the recommendation quality. For the traditional collaborative filtering recommendation algorithm, the similarity calculation is performed by a single user score, and the user's demand for the item cannot be accurately reflected. In order to solve this problem, the research proposes a distance-based scenic recommendation algorithm. The algorithm introduces the distance between the user and the item when performing the similarity calculation, then calculating the user's score on target scenic spots for recommendation. The experimental results show that, compared with the traditional collaborative filtering recommendation algorithm based on user score, the result of the distance-based scenic spot recommendation algorithm have some improvement in root-mean-square error, mean-absolute error, coverage, precision and f-measure.