Rapid development of the e-commerce, increase in the product range and customers in the past years makes it difficult to find the products that customers are looking for, in terms of customer made confusion and led to time losses. These developments have necessitated the development of new customer-oriented marketing strategy. Recommender system directs interests of customers to the product which they can like and buy. So the companies that use these systems increase profits by providing strategic advantages while helping customers. Collaborative Filtering (CF) is a successful technique used in recommendation system. They try to find out costumer’s interest in a new product, based on similarities of customers’ previous ratings. In the literature, these calculations are performed with the principle which is: similar users have similar tastes. In this paper these calculations are performed with thoughts that dissimilar users have dissimilar tastes, too. Currently algorithm of collaborative filtering suffers from some problems such as cold start and sparse data. At the same time this paper aims to propose ontology based solution for cold start problem.
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|