International Conference on Computer and Knowledge Engineering

Home / 12th International Conference on Computer and Knowledge Engineering

MCRS-SAE : multi criteria recommender system based on sparse autoencoder

Authors :

Amir reza Kalantarnezhad¹ Javad Hamidzadeh²

1- Sadjad University of Technology 2- Sadjad University of Technology

Keywords :

Multi-criteria recommender systems،deep learning،sparse auto encoder،radial basis function kernel

Abstract :

Due to the big amount of information in today’s world, recommender systems are used to help users reach the things that are most similar to their tastes. Compared to traditional recommender systems, Multi criteria recommender systems, consider several minor criteria instead of a general criterion, which cause predictions to be more similar to contents target user’s preferences. But high dimension and sparsity of data is always one of the main problems that reduce the quality of predictions. It has also been observed in recent years that the use of deep learning techniques in the field of recommender systems has increased quality of predictions. In addition, some criteria have more priority for the user during selecting item. In this paper, we propose a multi criteria recommender system using the sparse auto encoder (MCRS_SAE) to improve problem of sparsity of data and also use radial basis function kernel (RBF kernel) to determine the weight of the criteria. Experiments on the Yahoo! Movies and TripAdvisor multi-criteria datasets show that our proposed method in presenting personal predictions has better performance compared to other presented methods.