Mitigasi Bias Feedback Loops dalam Rekomendasi Buku Menggunakan Pendekatan Causal Adjustment
-
Yohanes Andika Dharma
*
Universitas Multi Data Palembang, Palembang,
Indonesia
- Daniel Udjulawa Universitas Multi Data Palembang, Palembang, Indonesia (*) Corresponding Author
Abstract
The digital publishing industry has experienced exponential growth over the past decade, with platforms such as Goodreads and Amazon cataloging over 50 million book titles available online (Ricci et al., 2022). This abundance of choices paradoxically creates difficulty for users to discover books that genuinely match their preferences. The book domain was specifically chosen due to its unique characteristics: a highly asymmetric consumption distribution (bestsellers dominate 80% of sales despite representing only 5% of titles), extreme genre and language diversity, and readers' need for intellectual exploration beyond mere popularity. Collaborative filtering-based recommender systems address this challenge but are vulnerable to feedback loops that reinforce popularity bias, causing popular books to receive excessive exposure while long-tail items are neglected. This problem is exacerbated by Missing Not at Random (MNAR) data. This study proposes CAFL-SVD, a Matrix Factorization model based on SVD integrated with the CAFL algorithm through IPS and K-Means cluster regularization. Evaluated on Book-Crossing dataset with 585,579 ratings, CAFL-SVD reduces Gini coefficient by 37.7% (0.5783 to 0.3601), achieves peak NDCG@5 of 0.6207, maintains 100% coverage, and average Novelty Score of 14.0, demonstrating that causal approaches can simultaneously improve recommendation fairness and relevance without significant accuracy sacrifice.
Downloads
References
Abuali, M. M., & Ghomeed, T. M. (2024). Utilizing the Artificial Bee Algorithm to Enhance the Accuracy of Book Recommendation Systems: A Case Study on Goodreads dataset. Libyan Journal of Contemporary Academic Studies, 54–62. https://ljcas.ly/index.php/ljcas/article/view/27
Chang, B., Meng, C., Ma, H., Chang, S., Gu, Y., Peng, Y., Feng, J., Zhang, Y., Bi, S., Chi, E. H., & Chen, M. (2024). Cluster Anchor Regularization to Alleviate Popularity Bias in Recommender Systems. WWW 2024 Companion - Companion Proceedings of the ACM Web Conference, 151–159. https://doi.org/10.1145/3589335.3648312
Chen, J., Dong, H., Wang, X., Feng, F., Wang, M., & He, X. (2023). Bias and Debias in Recommender System: A Survey and Future Directions. ACM Transactions on Information Systems, 41(3). https://doi.org/10.1145/3564284
Gao, C., Chen, R., Yuan, S., Huang, K., Yu, Y., & He, X. (2025). SPRec: Self-Play to Debias LLM-based Recommendation. WWW 2025 - Proceedings of the ACM Web Conference, 1, 5075–5084. https://doi.org/10.1145/3696410.3714524
Hussein, M. H., Alsakaa, A. A., & Marhoon, H. A. (2021). Adopting explicit and implicit social relations by SVD++ for recommendation system improvement. Telkomnika (Telecommunication Computing Electronics and Control), 19(2), 471–478. https://doi.org/10.12928/TELKOMNIKA.v19i2.18149
Khenissi, S., & Nasraoui, O. (2020). Modeling and Counteracting Exposure Bias in Recommender Systems. http://arxiv.org/abs/2001.04832
Krauth, K., Wang, Y., & Jordan, M. (2025). Breaking Feedback Loops in Recommender Systems with Causal Inference. ACM Transactions on Recommender Systems. https://doi.org/10.1145/3728372
Mendoza, M., & Torres, N. (2020). Evaluating content novelty in recommender systems. Journal of Intelligent Information Systems, 54(2), 297–316. https://doi.org/10.1007/s10844-019-00548-x
Qin, Z., Chen, S. J., Metzler, D., Noh, Y., Qin, J., & Wang, X. (2020). Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2359–2367. https://doi.org/10.1145/3394486.3403285
Ricci, F., Rokach, L., & Shapira, B. (2022). Recommender Systems: Techniques, Applications, and Challenges. Recommender Systems Handbook: Third Edition, 1–35. https://doi.org/10.1007/978-1-0716-2197-4_1
Saito, Y. (2020a). Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback. SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 309–318. https://doi.org/10.1145/3397271.3401114
Saito, Y. (2020b). Doubly Robust Estimator for Ranking Metrics with Post-Click Conversions. https://doi.org/10.
Saito, Y., Yaginuma, S., Nishino, Y., Sakata, H., & Nakata, K. (2020). Unbiased recommender learning from missing-not-at-random implicit feedback. WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining, 501–509. https://doi.org/10.1145/3336191.3371783
Verma, V., & Aggarwal, R. K. (2020). A comparative analysis of similarity measures akin to the Jaccard index in collaborative recommendations: empirical and theoretical perspective. Social Network Analysis and Mining, 10(1). https://doi.org/10.1007/s13278-020-00660-9
Wang, X., Zhang, R., Sun, Y., & Qi, J. (2019). Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random.
Wang, Y., Ma, W., Zhang, M., Liu, Y., & Ma, S. (2023). A Survey on the Fairness of Recommender Systems. ACM Transactions on Information Systems, 41(3). https://doi.org/10.1145/3547333
Wang, Z., Chen, X., Zhou, R., Dai, Q., Dong, Z., & Wen, J.-R. (2022). Sequential Recommendation with Causal Behavior Discovery. http://arxiv.org/abs/2204.00216
Xu, Y., Zhuang, F., Wang, E., Li, C., Wu, J., & Fellow, I. (2025). Learning without Missing-At-Random Prior Propensity-A Generative Approach for Recommender Systems.
Yang, L., Wang, C., Cui, Y., Belongie, S., Xuan, Y., & Estrin, D. (2018). Unbiased offline recommender evaluation for missing-not-at-random implicit feedback. RecSys 2018 - 12th ACM Conference on Recommender Systems, 279–287. https://doi.org/10.1145/3240323.3240355
Zhang, A., Ma, W., Zheng, J., Wang, X., & Chua, T. S. (2024). Robust Collaborative Filtering to Popularity Distribution Shift. ACM Transactions on Information Systems, 42(3). https://doi.org/10.1145/3627159
Zhang, R., Bao, H., Sun, H., Wang, Y., & Liu, X. (2016). Recommender systems based on ranking performance optimization. Frontiers of Computer Science, 10(2), 270–280. https://doi.org/10.1007/s11704-015-4584-1
Zhang, Y., Feng, F., He, X., Wei, T., Song, C., Ling, G., & Zhang, Y. (2021). Causal Intervention for Leveraging Popularity Bias in Recommendation. SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 11–20. https://doi.org/10.1145/3404835.3462875
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Mitigasi Bias Feedback Loops dalam Rekomendasi Buku Menggunakan Pendekatan Causal Adjustment
Pages: 2423-2432
Copyright (c) 2026 Yohanes Andika Dharma, Daniel Udjulawa
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
