Browse > Article
http://dx.doi.org/10.9708/jksci.2022.27.09.059

Methods Comparison: Enhancing Diversity for Personalized Recommendation with Practical E-Commerce Data  

Paik, Juryon (Dept. of Digital Information and Statistics, Pyeongtaek University)
Publication Information
Journal of the Korea Society of Computer and Information / v.27, no.9, 2022 , pp. 59-68 More about this Journal
Abstract
A recommender system covers users, searches the items or services which users will like, and let users purchase them. Because recommendations from a recommender system are predictions of users' preferences for the items which they do not purchase yet, it is rarely possible to be drawn a perfect answer. An evaluation has been conducted to determine whether a prediction is right or not. However, it can be lower user's satisfaction if a recommender system focuses on only the preferences, that is caused by a 'filter bubble effect'. The filter bubble effect is an algorithmic bias that skews or limits the information an individual user sees on the recommended list. It is the reason why multiple metrics are required to evaluate recommender systems, and a diversity metrics is mainly used for it. In this paper, we compare three different methods for enhancing diversity for personalized recommendation - bin packing, weighted random choice, greedy re-ranking - with a practical e-commerce data acquired from a fashion shopping mall. Besides, we present the difference between experimental results and F1 scores.
Keywords
Recommender system; Evaluation metrics; Relevance; Diversity; Filter bubble; Greedy re-ranking;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 S. Vargas and P/ Castells, "Rank and Relevance in Novelty and Diversity Metrics for Recommender Systems," Proceedings of the fifth ACM conference on Recommender systems (RecSys'11), October 2011, pp. 109-116, DOI:10.1145/2043932.2043955.   DOI
2 D. Jannach and M. Jugovac, "Measuring the Business Value of Recommender Systems," ACM Transactions on Management Information Systems, Vol. 10, No. 4, December 2019, pp 1-23, DOI:10.1145/3370082.   DOI
3 H. Na and K. Nam, "Application of diversity of recommender system according to user preference change," Journal of Intelligence and Information Systems, December 2020, Vol. 26, No. 4, pp. 67-86, DOI: 10.13088/JIIS.2020.26.4.067.   DOI
4 J. P. Kelly and D. Bridge, "Enhancing the diversity of conversational collaborative recommendations: a comparison," Artificial Intelligence Review Vol. 25, 2006, pp. 79-95, DOI:10.1007/s10462-007-9023-8.   DOI
5 P. Castells, N. J. Hurley, S. Vargas, "Novelty and Diversity in Recommender Systems," In: F. Ricci, F., L. Rokach, B. Shapira, (eds) Recommender Systems Handbook. Springer, 2015, pp. 881-918, DOI:10.1007/978-1-4899-7637-6_26.   DOI
6 M. Kaminskas and D. Bridge, "Diversity, serendipity, novelty, and coverage: A survey and empirical analysis of beyond-accuracy objectives in recommender systems," ACM Transactions on Interactive Intelligent Systems Vol.7, No.1, March 2017, pp.1-42, DOI:10.1145/2926720.   DOI
7 H. Park and K. Kim, "Recommender system using BERT sentiment analysis," Journal of Intelligence and Information Systems, Vol. 27, No. 2, June 2021, pp. 1-15. DOI: 10.13088/JIIS.2021.27.2.001.   DOI
8 S. Barry, "The Paradox of Choice: Why More Is Less," Ecco Press, Revised ed., ISBN 9780062449924, 2016.
9 A. I. Hariad, and D. Nurjanah, "Hybrid attribute and personality based recommender system for book recommendation," 2017 International Conference on Data and Software Engineering (ICoDSE), November 2017, pp. 1-5, DOI: 10.1109/ICODSE.2017.8285874.   DOI
10 D. Lee, "A to Z for Implementation of a Recommender System with Practical Data," 2021, fastcampus.co.kr.
11 D. Lee and K. Hosanagar, "How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment," Information Systems Research, Vol. 30, No. 1, Mar 2019, pp. 239-259, DOI: 10.1287/isre.2018.0800   DOI
12 F. O. Isinkayea, Y. O. Folajimib, and B. A. Ojokohcr, "Recommendation systems: Principles, methods and evaluation," Egyptian Informatics Journal, Vol. 16, No. 3, Nov. 2015, pp. 261-273, DOI: 10.1016/j.eij.2015.06.005.   DOI
13 X. Xie, J. Lian, Z. Liu, X. Wang, F. Wu, H. Wang, and Z. Chen "Personalized Recommendation Systems: Five Hot Research Topics You Must Know," Microsoft Research Lab - Asia, November 2018.
14 Gil Park, "Recommendation Algorithms and Hyper-Personalization," MOBIINSIDE, February 2021, https://www.mobiinside.co.kr/2021/02/01/algorithm-personalization/
15 J. Choi and H. J. Lee, "An Integrated Perspective of User Evaluating Personalized Recommender Systems: Performance-Driven or User-Centric," Journal of Society for e-Business Studies, Vol. 17, No. 3, 2012, pp. 85-103, DOI: 10.7838/JSEBS.2012.17.3.085.   DOI
16 M. Kim, "Evaluation Metrics for Recommender Systems," March 2021, mskim.log.