Forecasting Notarial Stamp Revenue Using Machine Learning: A Comparative Study at the Court of Justice of Goiás
Resumo
The predictability of notarial stamp revenue constitutes a critical challenge for budget planning in the Brazilian Judiciary. This study uses 74 months of data from the Sistema Extrajudicial Eletrônico (SEE), the electronic system used by the Court of Justice of Goiás to record and monitor notarial stamp transactions and revenue, covering Nov. 2019 to Dec. 2025, with IPCA as an exogenous variable, to compare statistical time-series and machine-learning models, including ARIMA, Prophet, XGBoost, LightGBM, hybrid models, and ensembles, under one-step-ahead and multi-step forecasting regimes. The multiplicative hybrid XGBoost achieved the best performance in the one-step setting (MAPE 3.14%, R2 = 0.738), while the weighted ensemble stood out in the multi-step setting (MAPE 3.04%, R2 = 0.770). As a practical contribution, an interactive Streamlit prototype was developed to support institutional decision-making in the TJGO.
Referências
Ben Taieb, S., Atiya, A. F., Bontempi, G., and Sorjamaa, A. (2012). A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Systems with Applications, 39(8):7067–7083.
Bergmeir, C., Hyndman, R. J., and Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120:70–83.
Bontempi, G., Ben Taieb, S., and Le Borgne, Y.-A. (2013). Machine learning strategies for time series forecasting. In Business Intelligence: Second European Summer School, eBISS 2012, Brussels, Belgium, July 15-21, 2012, Tutorial Lectures, pages 62–77. Springer, Berlin; Heidelberg.
Botchkarev, A. (2019). Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology. arXiv:1809.03006. Disponı̈vel em: [link]. Acesso em: 20 abr. 2026.
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time series analysis: forecasting and control. Wiley, Hoboken, 5 edition.
Cerqueira, V., Torgo, L., and Mozetič, I. (2020). Evaluating time series forecasting models: an empirical study on performance estimation methods. Machine Learning, 109:1997–2028.
Chen, T. and Guestrin, C. (2016). XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 785–794, San Francisco. ACM.
Diebold, F. X. and Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3):253–263.
Houssein, E. H., Mohamed, M., Younis, E. M. G., et al. (2025). Artificial intelligence and classical statistical models for time series forecasting: a comprehensive review. Journal of Big Data, 12:271.
Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts, Melbourne, 2 edition. Disponı̈vel em: [link]. Acesso em: 20 abr. 2026.
Hyndman, R. J. and Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4):679–688.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017), pages 3146–3154.
Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2022). Statistical and machine learning forecasting methods: concerns and ways forward. PLOS ONE, 17(3):e0264810.
Morettin, P. A. and Toloi, C. M. C. (2006). Análise de Séries Temporais. ABE – Manual do Usuário, 2 edition.
Shapiro, S. S. and Wilk, M. B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3/4):591–611.
Sina, L. B., Secco, C. A., Blazevic, M., and Nazemi, K. (2023). Hybrid forecasting methods—a systematic review. Electronics, 12(9):2019.
Taylor, S. J. and Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1):37–45.
Wirth, R. and Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, pages 29–39.
Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2):241–259.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50:159–175.
Zhou, Z.-H. (2012). Ensemble methods: foundations and algorithms. CRC Press, Boca Raton.
Bergmeir, C., Hyndman, R. J., and Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120:70–83.
Bontempi, G., Ben Taieb, S., and Le Borgne, Y.-A. (2013). Machine learning strategies for time series forecasting. In Business Intelligence: Second European Summer School, eBISS 2012, Brussels, Belgium, July 15-21, 2012, Tutorial Lectures, pages 62–77. Springer, Berlin; Heidelberg.
Botchkarev, A. (2019). Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology. arXiv:1809.03006. Disponı̈vel em: [link]. Acesso em: 20 abr. 2026.
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time series analysis: forecasting and control. Wiley, Hoboken, 5 edition.
Cerqueira, V., Torgo, L., and Mozetič, I. (2020). Evaluating time series forecasting models: an empirical study on performance estimation methods. Machine Learning, 109:1997–2028.
Chen, T. and Guestrin, C. (2016). XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 785–794, San Francisco. ACM.
Diebold, F. X. and Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3):253–263.
Houssein, E. H., Mohamed, M., Younis, E. M. G., et al. (2025). Artificial intelligence and classical statistical models for time series forecasting: a comprehensive review. Journal of Big Data, 12:271.
Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts, Melbourne, 2 edition. Disponı̈vel em: [link]. Acesso em: 20 abr. 2026.
Hyndman, R. J. and Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4):679–688.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017), pages 3146–3154.
Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2022). Statistical and machine learning forecasting methods: concerns and ways forward. PLOS ONE, 17(3):e0264810.
Morettin, P. A. and Toloi, C. M. C. (2006). Análise de Séries Temporais. ABE – Manual do Usuário, 2 edition.
Shapiro, S. S. and Wilk, M. B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3/4):591–611.
Sina, L. B., Secco, C. A., Blazevic, M., and Nazemi, K. (2023). Hybrid forecasting methods—a systematic review. Electronics, 12(9):2019.
Taylor, S. J. and Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1):37–45.
Wirth, R. and Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. In Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, pages 29–39.
Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2):241–259.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50:159–175.
Zhou, Z.-H. (2012). Ensemble methods: foundations and algorithms. CRC Press, Boca Raton.
Publicado
19/10/2026
Como Citar
SANTOS JÚNIOR, Renato Aparecido dos; AMORIM, Leonardo Afonso; SOUSA, Rafael Teixeira.
Forecasting Notarial Stamp Revenue Using Machine Learning: A Comparative Study at the Court of Justice of Goiás. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 706-717.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.30115.
