Application of Improved Collaborative Filtering Algorithm in Recommendation of Batik Products of Miao Nationality

Abstract

Recommendation system has been widely used in various e-commerce websites, but there are few personalized recommendations for ethnic handicrafts. And the national handicraft recommendation belongs to the small batch recommendation behavior, so the recommended performance is limited by the sparsity of the data in the scoring matrix. To solve this problem, an improved collaborative filtering algorithm is proposed, in which the user-based collaborative filtering algorithm is nested in the collaborative filtering algorithm based on gradient descent. First, the scoring prediction value is filled into the unscoring items in the scoring matrix, and then the recommendation is given by using the collaborative filtering method based on gradient descent. The proposed method is applied to the recommendation of wax dyeing products of Miao nationality and compared with the existing traditional methods. The results show that the improved algorithm greatly improves the recommendation performance, reduces the recommendation error and improves the accuracy.