DOI:
https://doi.org/10.14483/23448393.19925Published:
2023-02-28Issue:
Vol. 28 No. Suppl (2023): Bogotá, Committed with the Development of Science and TechnologySection:
Computational IntelligenceOptimization of Recommender Systems Using Particle Swarms
Optimización de sistemas recomendadores usando enjambre de partículas
Keywords:
unsupervised systems, Recommender systems, optimization using particle swarm, collaborative filters (en).Keywords:
Sistemas no Supervisados, Sistemas Recomendadores, Filtros Colaborativos, Optimización usando Enjambre de Partículas (es).Downloads
Abstract (en)
Background: Recommender systems are one of the most widely used technologies by electronic businesses and internet applications as part of their strategies to improve customer experiences and boost sales. Recommender systems aim to suggest content based on its characteristics and on user preferences. The best recommender systems are able to deliver recommendations in the shortest possible time and with the least possible number of errors, which is challenging when working with large volumes of data.
Method: This article presents a novel technique to optimize recommender systems using particle swarm algorithms. The objective of the selected genetic algorithm is to find the best hyperparameters that minimize the difference between the expected values and those obtained by the recommender system.
Results: The algorithm demonstrates viability given the results obtained, highlighting its simple implementation and the minimal and easily attainable computational resources necessary for its execution.
Conclusions: It was possible to develop an algorithm using the most convenient properties of particle swarms in order to optimize recommender systems, thus achieving the ideal behavior for its implementation in the proposed scenario.
Abstract (es)
Contexto: Los sistemas recomendadores son una de las tecnologías más ampliamente utilizadas por comercios electrónicos y aplicaciones de internet como parte de sus estrategias para mejorar la experiencia de sus clientes y aumentar sus ventas. El sistema recomendador tiene por objetivo sugerir contenido basado en las características del mismo y en las preferencias de los usuarios. Los mejores sistemas recomendadores deben estar en la capacidad de entregar las recomendaciones en el menor tiempo y con el menor error posibles, lo cual constituye un desafío cuando se trabaja con grandes volúmenes de datos.
Método: En este artículo se presenta una técnica novedosa para optimizar sistemas recomendadores utilizando algoritmos de enjambre de partículas. El objetivo del algoritmo genético seleccionado es encontrar los mejores hiperparámetros que minimicen la diferencia entre los valores esperados y los obtenidos por el sistema recomendador.
Resultados: El algoritmo demuestra viabilidad dados los resultados obtenidos, destacando que su implementación es sencilla y los recursos computacionales necesarios para su ejecución son mínimos y de fácil acceso.
Conclusiones: Fue posible desarrollar un algoritmo utilizando las propiedades más convenientes del enjambre de partículas para optimizar los sistemas recomendadores, logrando el comportamiento ideal para su implementación en el escenario planteado.
References
Z. Zhang and S. Qian, “The research of e-commerce recommendation system based on collaborative filtering technology,” in Advances in Computer Science and Information Engineering, D. Jin and S. Lin, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 507–512. https://doi.org/10.1007/978-3-642-30126-1_80 DOI: https://doi.org/10.1007/978-3-642-30126-1_80
L. Cegan and P. Filip, “Advanced web analytics tool for mouse tracking and real-time data processing,” in 2017 IEEE 14th International Scientific Conference on Informatics, 2017, pp. 431–435. https://doi.org/10.1109/INFORMATICS.2017.8327288 DOI: https://doi.org/10.1109/INFORMATICS.2017.8327288
A. Janusz, G. Hao, D. Kaluza, T. Li, R. Wojciechowski, and D. Slezak, “Predicting escalations in customer support: Analysis of data mining challenge results,” in 2020 IEEE International Conference on Big Data (Big Data), 2020, pp. 5519–5526. https://doi.org/10.1109/BigData50022.2020.9378024 DOI: https://doi.org/10.1109/BigData50022.2020.9378024
M. Wasid and V. Kant, “A particle swarm approach to collaborative filtering-based recommender systems through fuzzy features,” Procedia Comput. Sci., vol. 54, pp. 440–448, 2015. https://doi.org/10.1016/j.procs.2015.06.051 DOI: https://doi.org/10.1016/j.procs.2015.06.051
S. Ujjin and P. J. Bentley, "Particle swarm optimization recommender system," Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706), Indianapolis, IN, USA, 2003, pp. 124-131, https://doi.org/10.1109/SIS.2003.1202257 DOI: https://doi.org/10.1109/SIS.2003.1202257
J. Abernethy, F. Bach, T. Evgeniou, and J.-P. Vert, “Low-rank matrix factorization with attributes,” ArXiv, https://doi.org/10.48550/arXiv.cs/0611124
H. Hajimirsadeghi, A. Ghazanfari, A. Rahimi-Kian, and C. Lucas, “Cooperative coevolutionary invasive weed optimization and its application to Nash equilibrium search in electricity markets," 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC), Coimbatore, India, 2009, pp. 1532-1535, https://doi.org/10.1109/NABIC.2009.5393669 DOI: https://doi.org/10.1109/NABIC.2009.5393669
W. Zhou, X. Pan, R. Li, and Y. Lu, “The recommendation system based on semi-supervised pso clustering algorithm,” in Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016). Atlantis Press, 2017/03, pp. 63–71. [Online]. Available: https://doi.org/10.2991/ifmca-16.2017.11 DOI: https://doi.org/10.2991/ifmca-16.2017.11
A. Tjoa, M. Hofferer, G. Ehrentraut, and P. Untersmeyer, “Applying evolutionary algorithms to the problem ofinformation filtering,” in Database and Expert Systems Applications. 8th International Conference, DEXA ’97. Proceedings, 1997, pp. 450–458.
D. Heckerman, D. Chickering, C. Meek, R. Rounthwaite, and C. Kadie, “Dependency networks for collaborative filtering and data visualization.” J. Mach. Learn. Res., 01 2000, pp. 264–273.
D. Gutiérrez, A. Tapia Córdoba, and A. Rodríguez del Nozal. “Algoritmos Genéticos con Python: Un enfoque practico para resolver problemas de ingeniería”, Marcombo. Spain. 2020.
D. Nichols, “Implicit rating and filtering,” in Proceedings of the Fifth DELOS Workshop on Filtering and Collaborative Filtering. ERCIM, 1998, pp. 31–36, fifth DELOS Workshop on Filtering; Collaborative Filtering; Conference date: 01-01-1900.
L. Ungar and D. Foster, “Clustering methods for collaborative filtering,” Proceedings of the Workshop on Recommendation Systems, Conference: Proceeding of the 10th International Conference on Knowledge Management and Knowledge Technologies (I-KNOW 2010), 1-3 September, 2010, Graz, AustriaAt: Graz, Austria.
E. M.-M. Blanca Cecilia López-Ramírez, “Estudio del comportamiento en-línea de algoritmos bio-inspirados usando medidas de desempeño en optimización con restricciones” COMCEV’07, 3-5 october, 2007, Aguascalientes, México.
D. A. Demissie, “A Hybrid Movie Recommendation System using Particle Swarm Optimization and K-means Clustering Algorithm,” Ph.D. dissertation, Adama Science and Technology University (ASTU), June 2020.
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2023 Nancy Yaneth Gelvez Garcia, Jesús Gil-Ruíz, Jhon Fredy Bayona-Navarro
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
From the edition of the V23N3 of year 2018 forward, the Creative Commons License "Attribution-Non-Commercial - No Derivative Works " is changed to the following:
Attribution - Non-Commercial - Share the same: this license allows others to distribute, remix, retouch, and create from your work in a non-commercial way, as long as they give you credit and license their new creations under the same conditions.
2.jpg)
