earticle

영어

Recommender systems are now popular both commercially and in the research community, where many approaches have been suggested for providing recommendations. However, evaluating the affectivity of recommender systems is a challenging problem and most of the approaches used for evaluation are based on using some sort of a dataset. This paper describes a method for measuring the accuracy of a collaborative filtering based recommender systems called “User-Advertisement Simulation” that utilizes a simulation approach that creates artificial users and advertisements of a virtual market, then measures accuracy of the products’ ranking based on the user’s profile.