Performance analysis of neural networks-based multi-criteria recommender systems

Abstract

Frequent use of Internet applications and rapid growth of volumes of online resources have made it difficult for users to effectively make decisions on the kinds of information or items to select. Recommender systems (RSs) are intelligent decision-support tools that exploit users' preferences and suggest items that might be interesting to them. They are one of the various solutions used by online users to overcome the problem of information overload. Traditionally, RSs use single ratings to predict and represent preferences of users for items that are not yet seen. Multi-criteria RSs use multiple ratings to various items' attributes for improving prediction and recommendation accuracy of the systems. However, one major challenge of multi-criteria RSs is the choice of an efficient approach for modelling the criteria ratings. Therefore, this paper aimed at employing artificial neural networks to model the criteria ratings and determine the predictive performance of the systems based on aggregation function approach. Seven evaluation metrics have been used to evaluate and the accuracy of the systems. The empirical results of the study have shown that the proposed technique has the highest prediction and recommendation than the corresponding traditional technique.