The Research for Recommendation System Based on Improved KNN Algorithm
Bin Li, Sailuo Wan, Xia Hua, Fengshou Qian · 2020
In this paper, we have researched two basic tasks of recommendation system score prediction and Top-N recommendation. We have improved K nearest neighbor (IKNN) algorithm with compression and global effect. In experiments, the methods of Top-10 recommended mainly refer to the score on the basis of prediction. We recommended the items whose scores are the highest. The experimental results show that using IKNN algorithm recommendation system score predicted mean square difference (RMSE) has reduced significantly. Meanwhileit has a well recommendation precision improvement.