Development of a hybrid-based recommendation system
Abstract
Modern Internet and web services are flooded with a vast amount of information, which is becoming more challenging for users. Recommendation systems aim to address this information overload issue while personalizing the user experience by providing precise, personalized recommendations based on their preferences. The main goal of this work is implementing a recommendation system for a complex subject area and the algorithm of its integration into the sector of searching for the service providers. The article briefly outlines the main approaches and algorithms used in recommendation systems, highlighting their areas of application, advantages, and disadvantages, as well as description of the implementation of a recommendation system for a complex subject area and the algorithm for its integration into the sector of searching for the service providers. One distinctive feature of the system under development is the importance of geolocation data for the generation of recommendations. An algorithm for a hybrid recommendation system that combines knowledge-based and content-based filtering approaches has been developed. The advantages of the described algorithm include the absence of the need to store and use information about previous user sessions in the calculations, as well as addressing cold-start issues, generating real-time recommendations for the current user session, and solving the problem of determining the location for recommended establishments. The proposed approach can be used for developing and implementing recommendation algorithms in complex subject areas where geolocation data is crucial for providing recommendations.
Downloads
References
/References
MacKenzie, C. Meyer, S. Noble, How retailers can keep up with consumers. McKinsey & Company, 2013. URL: https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers (Last accessed: 29.08.2023).
C. C. Aggarwal, An Introduction to Recommender Systems. In Recommender Systems; Springer: Cham, Switzerland, 2016. URL: https://www.springer.com/gp/book/9783642031205 (Last accessed: 30.08.2023).
Yang X., Guo Y., Liu Y., Steck H., A survey of collaborative filtering based social recommender systems. Comput. Commun. 2014, 41, pp. 1–10. URL: https://www.sciencedirect.com/science/article/abs/pii/S0140366413001722 (Last accessed: 30.08.2023).
Ding Z., Li X., Jiang C, Zhou M., Objectives and state-of-the-art of location-based social network recommender systems. ACM Comput. Surv. CSUR 2018, 51, pp. 1–28. URL: https://dl.acm.org/doi/abs/10.1145/3154526 (Last accessed: 05.09.2023).
Z. Fayyaz, M. Ebrahimian, D. Nawara, A. Ibrahim, R. Kashef, Recommendation Systems: Algorithms, Challengers, Metrics, and Business. Appl. Sci., 2020. URL: https://www.mdpi.com/2076-3417/10/21/7748#B10-applsci-10-07748 (Last accessed: 05.09.2023).
B.M. Sarwar, G. Karypis, J.A. Konstan, J. Riedl, Item-based collaborative filtering recommendation algorithms. In WWW ’01, Proceedings of the 10th International Conference on World Wide Web, Hong Kong, China, 1–5 May 2001; Association for Computing Machinery: New York, NY, USA, 2001; Volume 1, pp. 285–295. URL: https://dl.acm.org/doi/abs/10.1145/371920.372071 (Last accessed: 05.09.2023).
J.B. Schafer, D. Frankowski, J. Herlocker, S. Sen, Collaborative filtering recommender systems. In The Adaptive Web; Springer: Berlin/Heidelberg, Germany, 2007; pp. 291–324. URL: https://link.springer.com/chapter/10.1007/978-3-540-72079-9_9 (Last accessed: 07.09.2023).
Al-Shamri, M.Y.H., User profiling approaches for demographic recommender systems. Knowl. Based Syst. 2016, 100, pp. 175–187. URL: https://www.sciencedirect.com/science/article/abs/pii/S0950705116001192 (Last accessed: 10.09.2023).
Deng F., Utility-based recommender systems using implicit utility and genetic algorithm. In Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering (MEIC-15), Shenyang, China, 1–3 April 2015; Atlantis Press: Amsterdam, The Netherlands, 2015. URL: https://www.atlantis-press.com/proceedings/meic-15/19830 (Last accessed: 11.09.2023).
R. Burke, Knowledge-based recommender systems. In Encyclopedia of Library and Information Systems; CRC Press: Boca Raton, FL, USA, 2000; Volume 69, (Suppl. 32), pp. 175–186. URL: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=dc133144d431fc3b75c8de27f6bb21da6eb5bc1b (Last accessed: 11.09.2023).
A.A. Kardan, M. Ebrahimi, A novel approach to hybrid recommendation systems based on association rules mining for content recommendation in asynchronous discussion groups. Inf. Sci. 2013, 219, pp. 93–110. URL: https://www.sciencedirect.com/science/article /abs/pii/S0020025512004756 (Last accessed: 18.09.2023).
I. MacKenzie, C. Meyer, S. Noble, How retailers can keep up with consumers. McKinsey & Company, 2013. URL: https://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers (Last accessed: 29.08.2023).
C. C. Aggarwal, An Introduction to Recommender Systems. In Recommender Systems; Springer: Cham, Switzerland, 2016. URL: https://www.springer.com/gp/book/9783642031205 (Last accessed: 30.08.2023).
Yang X., Guo Y., Liu Y., Steck H., A survey of collaborative filtering based social recommender systems. Comput. Commun. 2014, 41, pp. 1–10. URL: https://www.sciencedirect.com/science/article/abs/pii/S0140366413001722 (Last accessed: 30.08.2023).
Ding Z., Li X., Jiang C, Zhou M., Objectives and state-of-the-art of location-based social network recommender systems. ACM Comput. Surv. CSUR 2018, 51, pp. 1–28. URL: https://dl.acm.org/doi/abs/10.1145/3154526 (Last accessed: 05.09.2023).
Z. Fayyaz, M. Ebrahimian, D. Nawara, A. Ibrahim, R. Kashef, Recommendation Systems: Algorithms, Challengers, Metrics, and Business. Appl. Sci., 2020. URL: https://www.mdpi.com/2076-3417/10/21/7748#B10-applsci-10-07748 (Last accessed: 05.09.2023).
B.M. Sarwar, G. Karypis, J.A. Konstan, J. Riedl, Item-based collaborative filtering recommendation algorithms. In WWW ’01, Proceedings of the 10th International Conference on World Wide Web, Hong Kong, China, 1–5 May 2001; Association for Computing Machinery: New York, NY, USA, 2001; Volume 1, pp. 285–295. URL: https://dl.acm.org/doi/abs/10.1145/371920.372071 (Last accessed: 05.09.2023).
J.B. Schafer, D. Frankowski, J. Herlocker, S. Sen, Collaborative filtering recommender systems. In The Adaptive Web; Springer: Berlin/Heidelberg, Germany, 2007; pp. 291–324. URL: https://link.springer.com/chapter/10.1007/978-3-540-72079-9_9 (Last accessed: 07.09.2023).
Al-Shamri, M.Y.H., User profiling approaches for demographic recommender systems. Knowl. Based Syst. 2016, 100, pp. 175–187. URL: https://www.sciencedirect.com/science/article/abs/pii/S0950705116001192 (Last accessed: 10.09.2023).
Deng F., Utility-based recommender systems using implicit utility and genetic algorithm. In Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering (MEIC-15), Shenyang, China, 1–3 April 2015; Atlantis Press: Amsterdam, The Netherlands, 2015. URL: https://www.atlantis-press.com/proceedings/meic-15/19830 (Last accessed: 11.09.2023).
R. Burke, Knowledge-based recommender systems. In Encyclopedia of Library and Information Systems; CRC Press: Boca Raton, FL, USA, 2000; Volume 69, (Suppl. 32), pp. 175–186. URL: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=dc133144d431fc3b75c8de27f6bb21da6eb5bc1b (Last accessed: 11.09.2023).
A.A. Kardan, M. Ebrahimi, A novel approach to hybrid recommendation systems based on association rules mining for content recommendation in asynchronous discussion groups. Inf. Sci. 2013, 219, pp. 93–110. URL: https://www.sciencedirect.com/science/article /abs/pii/S0020025512004756 (Last accessed: 18.09.2023).
