IKB-MS - A Collaborative Filtering Approach Associated with Human Visual Attention for Clothing Recommendation

• Emilia Alves Nogueira UFU
• Ernani Viriato de Melo IFTM
• Elaine Ribeiro de Faria UFU
• Denise Guliato UFU

Resumo

Nowadays, the amount of customers using clothing sites for shopping is greatly increasing, mainly due to the easiness and rapidity of this way of consumption. In this context, Recommender Systems (RS) have become indispensable to help consumers to find products that may possibly pleasant or be useful to them. These systems often use techniques of Collaborating Filtering (CF). When there are items that do not have ratings or that possess quite few ratings available, the recommender system performs poorly. This problem is known as new item cold-start. In this paper, we propose to investigate in what extent information on visual attention can help to produce more accurate clothing recommendation models. We present a new collaborative filtering strategy that uses visual attention to characterize images and alleviate the new item cold-start problem. In order to validate this strategy, we created a clothing database and we use three algorithms well known for the extraction of visual attention these clothes. An extensive set of experiments shows that our approach is efficient and outperforms state-of-the-art CF RS.

Palavras-chave: Sistema de Recomendação, Filtragem Colaborativa, Atenção Visual, Partida a frio