Recommender System for Fashion Design

Abstract

Recommender system applies knowledge of discovery technique to the problem of making personalized recommendations for information, products, or services. In this paper, an effective framework for combining content and collaborative filtering is used to predict new items of interest for a user. In addition, association rule mining is used to search for interesting relationships among items in a given data set and recommend suitable pairs of items. The end-use of these patterns could be for feed back into the design process and for future decisions or, in this case, to automatically adapt aspects of the site based on previous usage patterns. The proposed system is efficient to improve the user’s satisfaction in the fashion design recommender system.