Paper Information | SBC BOOKS

Fill in your paper information

Language (*)

Title (*)

Keywords (*)

Abstract (*)

Recommender systems (RS) have become necessary tools for personalizing content and services across digital platforms, yet their confidence estimation remains a critical concern. Confidence estimation in RS aims to answer how confident the model is in its predictions. Despite the advances, integrating confidence into RS models often degrades performance, with outcomes strongly dependent on both dataset characteristics and architectural suitability. To investigate these issues, we conducted a comprehensive empirical study over established distribution-based confidence-aware models, OrdRec, CPMF, CBPMF, LBD, PRGAT, and PRLIGHTGCN. We further performed systematic capacity ablations on deeper models. The methodology combined expected calibration error, confidence-error correlation, rating distribution comparisons, and capacity-vs-performance ablation. Our results show that integrating confidence estimation does not consistently improve and can degrade point-estimate performance in recommendation models. Increasing model capacity fails to yield gains and can negatively impact performance, even in the training set, indicating optimization and data constraints. Moreover, calibration quality is not reliably aligned with predictive accuracy. These models may exhibit meaningful confidence–error correlation while remaining poorly calibrated in absolute terms.

Pages (*)

File Link

English Information

Title

Keywords

Abstract

(*) To change the order drag the item to the new position.

Authors

#	Name
1	Joel Pires(joelpires@ufba.br)
2	Eduardo da Silva(eduardo.ferreira1983@gmail.com)
3	Frederico Durão(fdurao@ufba.br)

(*) To change the order drag the item to the new position.

Reference

#	Reference
1	HEN, Q.; LI, X.; FANG, Y.; WANG, M. Advancing confidence calibration and quantification in medication recommendation. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, New York, NY, USA: Association for Computing Machinery, p. 106-117, 2025.
2	COSCRATO, V.; BRIDGE, D. Estimating and evaluating the uncertainty of rating predictions and top-n recommendations in recommender systems. ACM Trans. Recomm. Syst., v. 1, n. 2, 2023.
3	DA SILVA, D.; PIRES, J.; DURÃO, F. Exploiting surrogate submodular and cost-effective lazy forward algorithms for calibrated recommendations. In: Anais do XL Simpósio Brasileiro de Bancos de Dados, Porto Alegre, RS, Brasil: SBC, p. 98-111, 2025.
4	DE LOURDES M. SILVA, M. et al. Twix: Balancing fairness and utility in item exposure for recommendation systems. In: Anais do XL Simpósio Brasileiro de Bancos de Dados, Porto Alegre, RS, Brasil: SBC, p. 427-440, 2025.
5	DOS SANTOS, J. V. F. et al. Nova base de dados brasileira para sistemas de recomendação de artigos científicos. In: Anais do XL Simpósio Brasileiro de Bancos de Dados, Porto Alegre, RS, Brasil: SBC, p. 289-302, 2025.
6	GOLDBERG, K. et al. Eigentaste: A constant time collaborative filtering algorithm. Information Retrieval, v. 4, n. 2, p. 133-151, 2001.
7	HARPER, F. M.; KONSTAN, J. A. The movielens datasets: History and context. ACM Trans. Interact. Intell. Syst., v. 5, n. 4, 2015.
8	HE, R.; MCAULEY, J. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In: Proceedings of the 25th International Conference on World Wide Web, Republic and Canton of Geneva, CHE: International World Wide Web Conferences Steering Committee, p. 507-517, 2016.
9	KNYAZEV, N.; OOSTERHUIS, H. A lightweight method for modeling confidence in recommendations with learned beta distributions. In: Proceedings of the 17th ACM Conference on Recommender Systems, p. 306-317, 2023.
10	KOREN, Y.; SILL, J. Ordrec: an ordinal model for predicting personalized item rating distributions. In: Proceedings of the Fifth ACM Conference on Recommender Systems, New York, NY, USA: Association for Computing Machinery, p. 117-124, 2011.
11	NAEINI, M. P.; COOPER, G.; HAUSKRECHT, M. Obtaining well calibrated probabilities using bayesian binning. In: Proceedings of the AAAI Conference on Artificial Intelligence, v. 29, 2015.
12	NEGRÃO, A. et al. Mitigando impactos de distribuições não-iid em aprendizagem federada para sistemas de recomendação. In: Anais do XL Simpósio Brasileiro de Bancos de Dados, Porto Alegre, RS, Brasil: SBC, p. 413-426, 2025.
13	PIRES, J. M.; SILVA, E. F. D.; DURÃO, F. A. Exploiting distribution-based confidence integration in graph neural network recommenders. Applied Intelligence, v. 56, n. 5, p. 142, 2026.
14	WANG, C. et al. Confidence-aware matrix factorization for recommender systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, v. 32, 2018.
15	WU, L. Towards trustworthy graph neural networks and their applications in recommender systems. In: 2024 IEEE International Conference on Big Data (Big Data), p. 8250-8252, 2024.
16	XUE, H.-J. et al. Deep matrix factorization models for recommender systems. In: IJCAI, Melbourne, Australia, v. 17, p. 3203-3209, 2017.

Paper Registration

Fill in your paper information

English Information

Authors

Reference