Recommender systems provide their users an efficient way to handle with information overload problem by 4 offering personalized suggestions. Traditional recommender systems are based on two-dimensional user-item preference 5 matrix which constructed depending on the users' overall evaluations over items. However, they have begun to present 6 their preferences over under various circumstances. Thus, traditional recommendation techniques fail to process multi-7 criteria ratings during the

more »

... dation process. Multi-criteria recommender systems are an extension of traditional 8 recommender systems that utilize multi-criteria-based user preferences. Multi-criteria recommender systems provide more 9 personalized and accurate predictions compared to traditional recommender systems. However, the increased amount 10 of data dimension causes sparsity to be a major problem of such systems. Especially, the similarity-based multi-criteria 11 recommender systems may fail to find similar neighbors to an active user due to the lack of co-rated items among users. 12 Therefore, we propose a new similarity-based multi-criteria collaborative filtering approach based on autoencoders. In 13 order to handle with sparsity, the proposed method extracts non-linear, low-dimensional, dense features from raw and 14 sparse users'/items' preferences. Our experimental outcomes show that the proposed work can amortize the negative 15 impacts of sparsity over the accuracy comparing with the state-of-the-art multi-criteria recommendation techniques. 16