Geodesic
A new curve fitting based rating prediction algorithm for recommender systems
Kybernetika, Tome 58 (2022) no. 3, pp. 440-455

Voir la notice de l'article provenant de la source Czech Digital Mathematics Library

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 $\theta(n^2)$, for sparse matrices. Moreover, in the experiments we get slightly more accurate results compared to the known rating prediction algorithms.
DOI : 10.14736/kyb-2022-3-0440
Classification : 65D10, 68Q25, 68T01
Keywords: recommender systems; collaborative filtering; curve fitting 
@article{10_14736_kyb_2022_3_0440,
     author = {Ar, Yilmaz and Emrah Amrahov, \c{S}ahin and Gasilov, Nizami A. and Yigit-Sert, Sevgi},
     title = {A new curve fitting based rating prediction algorithm for recommender systems},
     journal = {Kybernetika},
     pages = {440--455},
     publisher = {mathdoc},
     volume = {58},
     number = {3},
     year = {2022},
     doi = {10.14736/kyb-2022-3-0440},
     zbl = {07613054},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2022-3-0440/}
}
TY  - JOUR
AU  - Ar, Yilmaz
AU  - Emrah Amrahov, Şahin
AU  - Gasilov, Nizami A.
AU  - Yigit-Sert, Sevgi
TI  - A new curve fitting based rating prediction algorithm for recommender systems
JO  - Kybernetika
PY  - 2022
SP  - 440
EP  - 455
VL  - 58
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2022-3-0440/
DO  - 10.14736/kyb-2022-3-0440
LA  - en
ID  - 10_14736_kyb_2022_3_0440
ER  - 
%0 Journal Article
%A Ar, Yilmaz
%A Emrah Amrahov, Şahin
%A Gasilov, Nizami A.
%A Yigit-Sert, Sevgi
%T A new curve fitting based rating prediction algorithm for recommender systems
%J Kybernetika
%D 2022
%P 440-455
%V 58
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2022-3-0440/
%R 10.14736/kyb-2022-3-0440
%G en
%F 10_14736_kyb_2022_3_0440
Ar, Yilmaz; Emrah Amrahov, Şahin; Gasilov, Nizami A.; Yigit-Sert, Sevgi. A new curve fitting based rating prediction algorithm for recommender systems. Kybernetika, Tome 58 (2022) no. 3, pp. 440-455. doi: 10.14736/kyb-2022-3-0440

Cité par Sources :