ACIAR Silvana Vanesa
congresos y reuniones científicas
Comparing product specifications to solve the cold start problem in a recommender system
SILVANA ACIAR; GABRIELA ACIAR; DEBBIE ZHANG
Congreso; Conferencia Latinoamericana en Informática (CLEI 2016); 2016
Recommender systems are widely used applications to solve the problems of information overload, usually on websites. A well-known problem of recommender systems is the problem of cold start, which is caused by the lack of data. A recommendation system can only produce good recommendations after it has accumulated enough data The problem becomes even more challenging when the recommender system comes to deal with new products or the products have not been evaluated by consumers. This paper addresses this problem based on a comparison of product specifications, experiments were conducted in the recommendation domain of digital cameras.