A NEW CURVE FITTING BASED RATING PREDICTION ALGORITHM FOR RECOMMENDER SYSTEMS


Creative Commons License

Ar Y., Amrahov Ş., Gasilov N., Yiğit Sert S.

KYBERNETIKA, vol.58, no.3, pp.440-455, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 58 Issue: 3
  • Publication Date: 2022
  • Doi Number: 10.14736/kyb-2022-3-0440
  • Journal Name: KYBERNETIKA
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Linguistic Bibliography, zbMATH
  • Page Numbers: pp.440-455
  • Keywords: recommender systems, collaborative filtering, curve fitting, MATRIX FACTORIZATION, SOCIAL NETWORKS, INFORMATION, ONTOLOGY
  • Ankara University Affiliated: Yes

Abstract

The most algorithms for Recommender Systems (RSs) are based on a Collaborative Filtering (CF) approach, in particular on the Probabilistic Matrix Factorization (PMF) method. It is known that the PMF method is quite successful for the rating prediction. In this study, we consider the problem of rating prediction in RSs. We propose a new algorithm which is also in the CF framework; however, it is completely different from the PMF-based algorithms. There are studies in the literature that can increase the accuracy of rating prediction by using additional information. However, we seek the answer to the question that if the input data does not contain additional information, how we can increase the accuracy of rating prediction. In the proposed algorithm, we construct a curve (a low-degree polynomial) for each user using the sparse input data and by this curve, we predict the unknown ratings of items. The proposed algorithm is easy to implement. The main advantage of the algorithm is that the running time is polynomial, namely it is theta(n2), for sparse matrices. Moreover, in the experiments we get slightly more accurate results compared to the known rating prediction algorithms.