Selection of clusters based on internal indices in multi-clustering collaborative filtering recommender system

• Autorzy: Kużelewska Urszula

Identyfikatory

DOI

10.24425/ijet.2024.149520

• Języki publikacji: EN

Abstrakty

EN

The successful application of a multi-clusteringbased neighborhood approach to recommender systems has led to increased recommendation accuracy and the elimination of divergence related to differences in clustering methods traditionally used. The Multi-Clustering Collaborative Filtering algorithm was developed to achieve this, as described in the author’s previous papers. However, utilizing multiple clusters poses challenges regarding memory consumption and scalability. Not all partitionings are equally advantageous, making selecting clusters for the recommender system’s input crucial without compromising recommendation accuracy. This article presents a solution for selecting clustering schemes based on internal indices evaluation. This method can be employed for preparing input data in collaborative filtering recommender systems. The study’s results confirm the positive impact of scheme selection on the overall recommendation performance, as it typically improves after the selection process. Furthermore, a smaller number of clustering schemes used as input for the recommender system enhances scalability and reduces memory consumption. The findings are compared with baseline recommenders’ outcomes to validate the effectiveness of the proposed approach.

Słowa kluczowe

EN

multi-clustering; collaborative filtering; evaluation of clustering schemes

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2024
• Tom: Vol. 70, No. 1
• Strony: 103--114
• Opis fizyczny: Bibliogr. 42 poz., rys., tab.

Twórcy

autor

Kużelewska Urszula

• Faculty of Computer Science, Bialystok Uni-versity of Technology, Wiejska 45a, 15-351 Bialystok, Poland

Bibliografia

• [1] C. C. Aggrawal, Recommender Systems. The Textbook. Yorktown Heights: Springer, 2016.
• [2] D. Jannach, Recommender Systems: an Introduction. New York: Cambridge University Press, 2010.
• [3] J. Haupt, “Last.fm: People-powered online radio,” Music Reference Services Quarterly, vol. 12, pp. 23-24, 2009.
• [4] Bennett, J. and Lanning, S. , “The Netflix prize,” in Proceedings of KDD Cup and Workshop, 2007.
• [5] Corbeil, J. and Florent, D., “Deploying a Cost-Effective and Production-Ready Deep News Recommender System in the Media Crisis Context,” in Proceedings of RecSys, 2020.
• [6] K. Chaudhari and T. Ankit, “A comprehensive survey on travel recommender systems,” Archives of Computational Methods in Engineering, vol. 27, no. 5, pp. 1545-1571, 2020.
• [7] O. C. Agbonifo and A. Motunrayo, “A development of an ontology-based personalised e-learning recommender system,” International Journal of Computer (IJC), vol. 38, no. 1, pp. 102-112, 2020.
• [8] X. Gao, F. Feng, H. Huang, X. Mao, T. Lan, and Z. Chi, “Food recommendation with graph convolutional network,” Information Sciences, vol. 584, pp. 170–183, 2022. [Online]. Available: doi: 10.1016/j.ins.2021.10.040
• [9] J. Díez, P. Pérez-Núñez, O. Luaces, B. Remeseiro, and A. Bahamonde, “Towards explainable personalized recommendations by learning from users’ photos,” Information Sciences, vol. 520, pp. 416-430, 2020. [Online]. Available: doi:10.1016/j.ins.2020.02.018
• [10] F. Ricci, L. Rokach, and B. Shapira, “Recommender systems: Introduction and challenges,” in Recommender Systems Handbook, 2015, pp.1-34.
• [11] J. Bobadilla, F. Ortega, A. Hernando, and A. Gutierrez, “Recommender systems survey,” Knowledge-Based Systems, vol. 46, pp. 109-132, 2013.
• [12] M. Singh, “Scalability and sparsity issues in recommender datasets: a survey,” in Knowledge and Information Systems, 2018, pp. 1-43.
• [13] Jannach, D. and Ludewig, M., “When recurrent neural networks meet the neighborhood for session-based recommendation,” in Proceedings of the Eleventh ACM Conference on Recommender Systems (RecSys17), 2017, p. 306-310.
• [14] V. Yadav1, R. Shukla, A. Tripathi, and A. Maurya, “A new approach for movie recommender system using k-means clustering and pca,” Journal of Scientific & Industrial Research, vol. 80, pp. 159-165, 2021.
• [15] L. Kaufman, Finding Groups in Data: An Introduction to Cluster Analysis. New York: John & Sons Wiley, 2009.
• [16] J. Bailey, “Alternative clustering analysis: a review,” in Intelligent Decision Technologies: Data Clustering: Algorithms and Applications. Boca Raton: Chapman and Hall/CRC, 2014, pp. 533-548.
• [17] T. Li, M. Ogihara, and S. Ma, “On combining multiple clusterings: An overview and a new perspective,” Applied Intelligence, vol. 33, no. 2, pp. 207-219, 2010.
• [18] U. Kużelewska, “Effect of Dataset Size on Efficiency of Collaborative Filtering Recommender Systems with Multi-clustering as a Neighbour-hood Identification Strategy,” in International Conference on Computational Science. New York: Springer, 2020, pp. 342-354.
• [19] U. Kużelewska, “Scheme Selection based on Clusters’ Quality in Multi-Clustering M-CCF Recommender System,” in 31st International Conference on Information Systems Development (ISD 2023), 2023.
• [20] S. Latifi, N. Mauro, and D. Jannach, “Session-aware recommendation: A surprising quest for the state-of-the-art,” Information Sciences, vol. 573, pp. 291-315, 2021. [Online]. Available: doi:10.1016/j.ins.2021.05.048
• [21] R. Kuo, C. Chen, and S. Keng, “Application of hybrid metaheuristic with perturbation-based k-nearest neighbors algorithm and densest imputation to collaborative filtering in recommender systems,” Information Sciences, vol. 575, pp. 90-115, 2021. [Online]. Available: doi:10.1016/j.ins.2021.06.026
• [22] Y. Kilani, A. Otoom, A. Alsarhan, and M. Almaayah, “A genetic agorithms-based hybrid recommender system of matrix factorization and neighborhood-based techniques,” Journal of Computational Science, vol. 28, pp. 78-93, 2018. [Online]. Available: doi:10.1016/j.jocs.2018.08.007
• [23] U. Kużelewska, “Dynamic Neighbourhood Identification Based on Multi-clustering in Collaborative Filtering Recommender Systems,” in International Conference on Dependability and Complex Systems, 2020, pp. 410-419.
• [24] Yaoy, S. and Yuy, G. and Wangy, X. and Wangy, J. and Domeniconiz, C. and Guox, M., “Discovering Multiple Co-Clusterings in Subspaces,” in Proceedings of the 2019 SIAM International Conference on Data Mining, 2019, pp. 423-431.
• [25] A. Bilge and H. Polat, “A scalable privacy-preserving recommendation scheme via bisecting k-means clustering,” Information Process Management, vol. 49, no. 4, pp. 912-927, 2013.
• [26] M. Farahani, J. Torkestani, and M. Rahmani, “Adaptive personalized recommender system using learning automata and items clustering,” Information Systems, vol. 106, p. 101978, 2022. [Online]. Available: doi:10.1016/j.is.2021.101978
• [27] Rashid, M. and Shyong, K. L. and Karypis, G. and Riedl, J., “ClustKNN a Highly Scalable Hybrid Model - Memory-based CF Algorithm,” in Proceeding of WebKDD, 2006.
• [28] L. R. Divyaa and N. Pervin, “Towards generating scalable personalized recommendations: Integrating social trust, social bias, and geo-spatial clustering,” Decision Support Systems, vol. 122, 2019.
• [29] R. Logesh, V. Subramaniyaswamy, D. Malathi, N. Sivaramakrishnan, and V. Vijayakumar, “Enhancing recommendation stability of collaborative filtering recommender system through bioinspired clustering ensemble method,” Neural Computing and Applications, vol. 32, pp. 2141-2164, 2020.
• [30] S. Kant and T. Mahara, “Nearest biclusters collaborative filtering framework with fusion,” Journal of Computational Science, vol. 25, pp. 204-212, 2018. [Online]. Available: doi:10.1016/j.jocs.2017.03.018
• [31] F. de Aguiar Neto, A. da Costa, M. Manzato, and R. Campello, “Preprocessing approaches for collaborative filtering based on hierarchical clustering,” Information Sciences, vol. 534, pp. 172002D191, 2020. [Online]. Available: doi:10.1016/j.ins.2020.05.021
• [32] S. Bansal and N. Baliyan, “Bi-mars: A bi-clustering based memetic algorithm for recommender systems,” Applied Soft Computing, vol. 97, p. 106785, 2020. [Online]. Available: doi:10.1016/j.asoc.2020.106785
• [33] P. Fränti and S. Sieranoja, “How much can k-means be improved by using better initialization and repeats?” Pattern Recognition, vol. 93, pp. 95-112, 2019.
• [34] A. Strehl and J. Ghosh, “Cluster ensembles - a knowledge reuse frame-work for combining multiple partitions,” Journal of Machine Learning Research, vol. 3, pp. 583-617, 2002.
• [35] L. Bai, Y. Liang, and F. Cao, “A multiple k-means clustering ensemble algorithm to find nonlinearly separable clusters,” Information Fusion, vol. 61, pp. 36-47, 2020. [Online]. Available: doi:10.1016/j.inffus.2020.03.009
• [36] S. Zahra, M. A. Ghazanfar, A. Khalid, M. A. Azam, U. Naeem, and A. Prugel-Bennett, “Novel centroid selection approaches for kmeans-clustering based recommender systems,” Information Sciences, vol. 320, pp. 156-189, 2015. [Online]. Available: doi:10.1016/j.ins.2015.03.062
• [37] P. J. Rousseeuw, “Silhouettes a graphical aid to the interpretation and validation of cluster analysis,” Computational and Applied Mathematics, vol. 20, p. 53-65, 1987.
• [38] D. L. Davies and D. W. Bouldin, “A cluster separation measure,” PAMI-IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 1,no. 2, pp. 224-227, 1979.
• [39] T. Caliński and J. Harabasz, “A dendrite method for cluster analysis,” Communications in Statistics - Theory and Methods, vol. 3, pp. 1-27, 1974.
• [40] “Movielens dataset.” [Online]. Available: https://grouplens.org/datasets/movielens/25m/
• [41] F. Pedregosa, “Scikit-learn: Machine learning in python,” JMLR, vol. 12, pp. 2825-2830, 2011.
• [42] J. Miles, R squared adjusted R squared. New York: Wiley StatsRef: Statistics Reference Online, 2014. [Online]. Available: doi:10.1002/9781118445112.stat06627

Uwagi

1. Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).

2. The work was supported by a grant from the Bialystok University of Technology WZ/WI-IIT/3/2023 and funded with resources for research by the Ministry of Education and Science in Poland.