Detection of Concept Drifts in the ICMS Revenue Time Series of the State of Sergipe

• Arthur Fernando da Silva Santos Estácio
• Anthony Eduardo Medeiros Pantaleão Estácio
• Max Castor Rodrigues Junior Estácio
• Yúri Faro Dantas de Sant’Anna Estácio

DOI: https://doi.org/10.5753/erbase.2025.12975

Abstract

The collection of the Tax on the Circulation of Goods and Services (ICMS) is the main source of revenue for the State of Sergipe, essential for funding public policies. Understanding variations in the time series can support strategic government decisions. This study proposed the evaluation and selection of a concept drift detection algorithm in time series, aiming to identify significant changes in the monthly ICMS revenue. Different detectors with distinct mechanisms were tested. The Bottom-up algorithm showed the best performance among the explored options, achieving a score of 5.38 in the MTR metric, which combines a low false alarm rate and fast detection. In this context, the model proves to be a promising, efficient, and viable option for real-world applications.

References

Agrahari, S. and Singh, A. K. (2022). Concept drift detection in data stream mining : A literature review. Journal of King Saud University - Computer and Information Sciences, 34(10, Part B):9523–9540.

Brasil (1996). Lei nº 3.796, de 26 de dezembro de 1996. [link]. Dispõe sobre o ICMS no Estado de Sergipe.

Brasil (2000). Lei n.º 9.964, de 10 de abril de 2000. [link]. Institui o Programa de Recuperação Fiscal – REFIS, destinado à regularização de débitos junto à Receita Federal e ao INSS.

da Fonseca, J. L. D., Almeida, C. R. d. C., and da Silva, M. d. R. (2021). Impactos na arrecadação nos estados do nordeste na pandemia da covid-19. Revista Conhecimento Contábil, 11(2).

de Sant’Anna, Y. F. D., de Farias, M. L., Júnior, M. C., Dantas, D., and Junior, M. R. (2024). Fuel classification in electronic tax documents. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, pages 337–343. INSTICC, SciTePress.

Florez, A., Rodríguez-Moreno, I., Florez-Tapia, A. M., Artetxe, A., and Sierra, B. (2025). Lynxsight: change-point detection through different distance-based common spatial patterns. The Journal of Supercomputing, 81(7):858.

Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., and Bouchachia, H. (2014). A survey on concept drift adaptation. ACM Computing Surveys (CSUR), 46.

Hu, L., Lu, Y., and Feng, Y. (2025). Concept drift detection based on deep neural networks and autoencoders. Applied Sciences, 15(6).

Iwashita, A. and Papa, J. (2018). An overview on concept drift learning. IEEE Access, PP:1–1.

JAYACHANDRAN, B. (2021). Changepoint detection with python on sensor data in welding processes. Master of science thesis, POLITECNICO DI TORINO, Torino.

Killick, R., Fearnhead, P., and and, I. A. E. (2012). Optimal detection of changepoints with a linear computational cost. Journal of the American Statistical Association, 107(500):1590–1598.

Kronberg, S. (2024). Concept drift detection in document classification: An evaluation of adwin, kswin, and page hinkley using different observation variables.

Lima, M., Neto, M., Filho, T. S., and de A. Fagundes, R. A. (2022). Learning under concept drift for regression—a systematic literature review. IEEE Access, 10:45410–45429.

Liu, J., Yang, D., Zhang, K., Gao, H., and Li, J. (2023). Anomaly and change point detection for time series with concept drift. World Wide Web, 26(5):3229–3252.

Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., and Zhang, G. (2019). Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12):2346–2363.

Lukats, D., Zielinski, O., Hahn, A., and Stahl, F. (2024). A benchmark and survey of fully unsupervised concept drift detectors on real-world data streams. International Journal of Data Science and Analytics, 19:1–31.

M., B. and I.V., N. (1993). Detection of Abrupt Changes: Theory and Application. Prentice-Hall, Inc.

Rezende, F. (2009). A reforma tributária e a Federação. Fundação Getúlio Vargas.

SEBASTIÃO, R. and FERNANDES, J. M. (2017). Supporting the page-hinkley test with empirical mode decomposition for change detection. In Proceedings of the International Symposium on Methodologies for Intelligent Systems, pages 492–498, Rasdorf, Germany. Springer International Publishing.

SILVA, P. d. (2013). O icms como reflexo do desenvolvimento econômico dos municípios do estado de sergipe. Master’s thesis, Universidade Federal de Sergipe.

TRUONG, C., OUDRE, L., and VAYATIS, N. (2018). Ruptures: change point detection in python. arXiv, abs/1801.00826. Disponível em: [link]. Acesso em: 21 abr. 2025.

TRUONG, C., OUDRE, L., and VAYATIS, N. (2020). Selective review of offline change point detection methods. IEEE Signal Processing Magazine, 37(6):104–116.

Urso, A., Fiannaca, A., La Rosa, M., Ravı̀, V., and Rizzo, R. (2018). Data mining: Classification and prediction. Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics, 384.

Wang, S., Schlobach, S., and Klein, M. (2011). Concept drift and how to identify it. Journal of Web Semantics, 9(3):247–265. Semantic Web Dynamics Semantic Web Challenge, 2010.

Yeshchenko, A., Mendling, J., Di Ciccio, C., and Polyvyanny, A. (2020). Vdd: A visual drift detection system for process mining. In CEUR Workshop Proceedings, pages 31–34.

You, X., Zhang, M., Ding, D., Feng, F., and Huang, Y. (2021). Learning to learn the future: Modeling concept drifts in time series prediction. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2434–2443.