Time Series Forecasting of Public Revenues and Expenditures: A Comparative Analysis of Individual, Local, and Global Approaches

• Ruam Pastor UFPE
• Hemir da C. Santiago UPE
• Paulo S. G. de Mattos Neto UFPE
• Bernardo Silva SEPLAG-PE
• Newton Cerezini SEPLAG-PE

DOI: https://doi.org/10.5753/eniac.2026.31171

Resumo

Public revenue and expenditure forecasting is essential for fiscal planning, yet remains relatively underexplored from a machine learning perspective. This study investigates the performance of three learning paradigms for multiple time series forecasting, individual, local, and global, applied to real public finance data from the State of Pernambuco, Brazil. The paper employs a range of traditional statistical models, machine learning methods, and foundation models, encompassing 13 different combinations. The results indicate that no single approach is universally superior, as performance depends on the specific dataset. While the evaluated approaches performed similarly for revenues, the global approach showed better results for expenditures. These findings highlight how foundation models can complement domain-specific training, providing practical evidence for choosing the most suitable forecasting strategy in public finance.

Referências

Aghabozorgi, S., Seyed Shirkhorshidi, A., and Ying Wah, T. (2015). Time-series clustering — a decade review. Information Systems, 53:16–38.

Aksu, T., Woo, G., Liu, J., Liu, X., Liu, C., Savarese, S., Xiong, C., and Sahoo, D. (2024). Gift-eval: A benchmark for general time series forecasting model evaluation. arXiv preprint arXiv:2410.10393.

Ansari, A. F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., Shchur, O., Rangapuram, S. S., Arango, S. P., Kapoor, S., et al. (2024). Chronos: Learning the language of time series. arXiv preprint arXiv:2403.07815.

Bandara, K., Bergmeir, C., and Smyl, S. (2020). Forecasting across time series databases using recurrent neural networks on groups of similar series: a clustering approach. Expert Systems with Applications, 140:112896.

Barchi, T. M., Dos Santos, J. L. F., Alves, T. A., de Mattos Neto, P. S., Stevan Jr, S. L., Corrêa, F. C., Medina, M. C. C., Siqueira, H. V., and de Oliveira, J. F. L. (2026). A genetic algorithm-based ensemble framework for wind speed forecasting. Scientific Reports.

Batóg, B. and Batóg, J. (2021). Regional government revenue forecasting: Risk factors and accuracy. Risks, 9(12).

Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control. John Wiley & Sons, Hoboken, NJ, 5 edition.

Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.

Buettner, T. and Kauder, B. (2010). Revenue forecasting practices: differences across countries and consequences for forecasting performance. Fiscal Studies, 31(3):313–340.

Congressional Budget Office (2024). An update to the budget and economic outlook: 2024 to 2034. Technical report, Congressional Budget Office. Accessed: 2026-06-22.

Duarte, F. C., Neto, P. S., and Firmino, P. R. (2025). Improving accuracy in short mortality rate series: Exploring multi-step forecasting approaches in hybrid systems. arXiv preprint arXiv:2509.22395.

Hewamalage, H., Ackermann, K., and Bergmeir, C. (2023). Forecast evaluation for data scientists: common pitfalls and best practices. Data Mining and Knowledge Discovery, 37(2):788–832.

Jonung, L. and Larch, M. (2006). Improving fiscal policy in the EU: the case for independent forecasts. Economic Policy, 21(47):491–534.

Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2018). The M4 competition: Results, findings, conclusion and way forward. International Journal of Forecasting, 34(4):802–808.

Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2022). The M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting, 38(4):1346–1364.

Masini, R. P., Medeiros, M. C., and Mendes, E. F. (2023). Machine learning advances for time series forecasting. Journal of Economic Surveys, 37(1):76–111.

Montero-Manso, P. and Hyndman, R. J. (2021). Principles and algorithms for forecasting groups of time series: Locality and globality. International Journal of Forecasting, 37(4):1632–1653.

Padilha, G. A. G., Jung, J. J., and de Mattos Neto, P. S. (2025). Memetic algorithm-based optimization of hybrid forecasting systems for multivariate time series. Neural Computing and Applications, 37(17):10689–10706.

Petropoulos, F., Apiletti, D., Assimakopoulos, V., Babai, M. Z., Barrow, D. K., Ben Taieb, S., Bergmeir, C., Bessa, R. J., Bijak, J., Boylan, J. E., et al. (2022). Forecasting: theory and practice. International Journal of Forecasting, 38(3):705–871.

Safari, M. J. S., Arashloo, S. R., and Vaheddoost, B. (2025). Signature kernel ridge regression time series model: A novel approach for hydrological drought modeling using multi-station meteorological drought information. Applied Soft Computing, 178:113343.