Predictive models for cash flow management in public administration: application in the investment unit of the Medellín district
DOI:
https://doi.org/10.61799/2216-0388.1752Keywords:
Time series analysis, cash flow, public financial management, forecasting models, strategic planningAbstract
Efficient cash flow management is crucial for resource administration in the public sector, especially in entities such as the Investment Unit of the Medellín Mayor’s Office, where liquidity and investment decisions directly influence the development of strategic programs and projects. The purpose of this research is to identify the forecasting methodology with the best performance for estimating the future behavior of the main income categories in the unit’s cash flow, thereby contributing to financial planning and liquidity management optimization. A quantitative approach was adopted using an analytical-synthetic method, beginning with a literature review on forecasting models applied in both the public and private sectors. A time-series analysis followed this to identify patterns and trends across the primary income categories. Subsequently, forecasting models based on the Box-Jenkins methodology, the classical Holt-Winters model, and autoregressive neural networks from machine learning were applied. These models were evaluated using performance indicators to determine which best fit each series' behavior. The results show that the optimal model varies across time series and allows for projections that align with the unit’s financial reality. This highlights the importance of implementing advanced analytical tools in public sector financial management, as they enhance decision-making and promote efficient resource allocation. In conclusion, the use of predictive models strengthens the planning capacity and financial sustainability of the Medellín Mayor’s Office, serving as a reference for other governmental entities with similar liquidity management needs.
Downloads
References
[1] Alcaldía de Medellín, “¿Qué hace la Secretaría de Hacienda?,” Secretarias y Dependencias. [Online]. Available: https://www.medellin.gov.co/es/secretaria-de-hacienda/funciones-y-composicion/
[2] I. Iskandar, R. Willett, and S. Xu, “The development of a government cash forecasting model,” Journal of Public Budgeting, Accounting & Financial Management, vol. 30, no. 4, pp. 368–383, Nov. 2018, doi: 10.1108/JPBAFM-04-2018-0036.
[3] L. E. Velasco Baños, G. Martínez Prats, and T. F. Morales Cárdenas, “IMPORTANCIA DEL ESTADO DE FLUJO DE EFECTIVO EN LAS PYMES,” Revista Facultad de Ciencias Contables Económicas y Administrativas -FACCEA, vol. 12, no. 1, pp. 110–119, Feb. 2022, doi: 10.47847/faccea.v12n1a7.
[4] C. Cangoz and L. Secunho, “Cash management: how do countries perform sound practices?,” Revista Nacional de Administración, vol. 12, no. 1, p. e3572, Jun. 2021, doi: 10.22458/rna.v12i1.3572.
[5] F. Laghari, F. Ahmed, and M. de las N. López García, “Cash flow management and its effect on firm performance: Empirical evidence on non-financial firms of China,” PLoS One, vol. 18, no. 6, p. e0287135, Jun. 2023, doi: 10.1371/journal.pone.0287135.
[6] A. Mohammadi, “Dynamic Cash Flow Management Under Uncertainty: Integrating Scenario Planning and Advanced Analytical Tools,” International Journal of applied Research in Management, Economics and Accounting, vol. 2, no. 1, pp. 23–34, Dec. 2024, doi: 10.63053/ijmea.32.
[7] G. Rompotis, “Cash flow management, performance and risk: evidence from Greece,” EuroMed Journal of Business, Feb. 2024, doi: 10.1108/EMJB-09-2023-0245.
[8] M. Kotb, M. A. R. Ibrahim, and Y. S. Al-Olayan, “A Study of the Cash Flow Forecasting Impact on the Owners Financial Management of Construction Projects in the State of Kuwait,” Asian Business Research, vol. 3, no. 1, p. 69, Feb. 2018, doi: 10.20849/abr.v3i1.351.
[9] J. Lewellen and K. Lewellen, “Investment and Cash Flow: New Evidence,” Journal of Financial and Quantitative Analysis, vol. 51, no. 4, pp. 1135–1164, Aug. 2016, doi: 10.1017/S002210901600065X.
[10] Z. Wang, “The Effect of Internal Cash Flow on the Investment of Chinese Listed Companies,” School of Economics and Management, Changsha University of Science and Technology, vol. 11, no. 1, pp. 1–14, 2009, doi: DOI 10.1109/BIFE.2009.192.
[11] J. Rodríguez, “Flujo de caja. Herramienta clave para la toma de decisiones en la microempresa,” Panorama, vol. 2, no. 4, 2008. URL: https://dialnet.unirioja.es/servlet/articulo?codigo=4780127
[12] A. B. Sekar Mayangsari, “The Role Of Cash Planning In Budget Absorption: Perception Testing,” Jurnal Akuntansi, vol. 25, no. 2, p. 201, Aug. 2021, doi: 10.24912/ja.v25i2.806.
[13] C. Andreas et al., “Comparison study using ARIMAX and VARX in cash flow forecasting,” 2022, p. 030023. doi: 10.1063/5.0118519.
[14] K. Levy, K. E. Chasalow, and S. Riley, “Algorithms and Decision-Making in the Public Sector,” Annu Rev Law Soc Sci, vol. 17, no. 1, pp. 309–334, Oct. 2021, doi: 10.1146/annurev-lawsocsci-041221-023808.
[15] Salas-Molina, F., Martin, F. J., Rodríguez-Aguilar, J. A., Serrà, J., & Arcos, J. Ll. (2017). Empowering cash managers to achieve cost savings by improving predictive accuracy. International Journal of Forecasting, 33(2), 403-415. https://doi.org/10.1016/j.ijforecast.2016.11.002
[16] B. Małkus and G. J. Nalepa, “Forecasting Daily Cash Flows in a Company - Shortcoming in the Research Field and Solution Exploration,” 2023, pp. 360–369. doi: 10.1007/978-3-031-25599-1_27.
[17] S. Semenova, “Cash Flow Forecasting in the Valuation of Financial Instruments,” Проблеми сучасних трансформацій. Серія: економіка та управління, no. 16, Dec. 2024, doi: 10.54929/2786-5738-2024-16-09-07.
[18] B. Małkus and G. J. Nalepa, “Forecasting Daily Cash Flows in a Company - Shortcoming in the Research Field and Solution Exploration,” 2023, pp. 360–369. doi: 10.1007/978-3-031-25599-1_27.
[19] M. Monica, A. Suharsono, B. W. Otok, and A. Wibisono, “Hybrid SARIMA-FFNN model in forecasting cash outflow and inflow,” J Phys Conf Ser, vol. 2106, no. 1, p. 012002, Nov. 2021, doi: 10.1088/1742-6596/2106/1/012002.
[20] A. Suharsono, M. Monica, B. W. Otok, and A. Wibisono, “Modelling and forecasting cash outflow-inflow using ARIMA-Feedforward Neural Network,” 2022, p. 020016. doi: 10.1063/5.0108037.
[21] S. Gelper, R. Fried, and C. Croux, “Robust Forecasting with Exponential and Holt-Winters Smoothing,” SSRN Electronic Journal, 2007, doi: 10.2139/ssrn.1089403.
[22] J. C. Valderrama-Balaguera, H. F. Castro-Silva, and C. A. Dávila Carrillo, “Pronósticos de variables climatológicas mediante los modelos de punto de cambio y Holt-Winters,” Mundo FESC, vol. 11, no. S2, pp. 337–352, Sep. 2021, doi: 10.61799/2216-0388.986.
[23] H. de J. Gallardo-Pérez, M. Vergel-Ortega, and J. P. Rojas-Suárez, “Análisis dinámico de series temporales multivariadas,” Mundo FESC, vol. 10, no. 20, pp. 41–49, Jul. 2020, doi: 10.61799/2216-0388.618.
[24] K. Dadteev, B. Shchukin, and S. Nemeshaev, “Using artificial intelligence technologies to predict cash flow,” Procedia Comput Sci, vol. 169, pp. 264–268, 2020, doi: 10.1016/j.procs.2020.02.163.
[25] I. Evdokimov, M. Kampouridis, and T. Papastylianou, “Application Of Machine Learning Algorithms to Free Cash Flows Growth Rate Estimation,” Procedia Comput Sci, vol. 222, pp. 529–538, 2023, doi: 10.1016/j.procs.2023.08.191.
[26] P. Peng, Y. Chen, W. Lin, and J. Z. Wang, “Attention-based CNN–LSTM for high-frequency multiple cryptocurrency trend prediction,” Expert Syst Appl, vol. 237, p. 121520, Mar. 2024, doi: 10.1016/j.eswa.2023.121520.
[27] H. Weytjens, E. Lohmann, and M. Kleinsteuber, “Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet,” Electronic Commerce Research, vol. 21, no. 2, pp. 371–391, Jun. 2021, doi: 10.1007/s10660-019-09362-7.
[28] Karatas, T., Klinkert, F., & Hirsa, A. (2021). Supervised Neural Networks for Illiquid Alternative Asset Cash Flow Forecasting. arXiv. https://doi.org/10.48550/arXiv.2108.02853.
[29] Z. Dong and Y. Zhou, “A Novel Hybrid Model for Financial Forecasting Based on CEEMDAN-SE and ARIMA-CNN-LSTM,” Mathematics, vol. 12, no. 16, p. 2434, Aug. 2024, doi: 10.3390/math12162434.
[30] Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial Time Series Forecasting with Deep Learning: A Systematic Literature Review: 2005-2019. arXiv. https://doi.org/10.48550/arXiv.1911.13288
[31] F. A. Fernández Gelvez, L. Jaimes Cerveleón, and L. E. Mendoza, “Modelo de regresión basado en máquinas de aprendizaje utilizando datos estadísticos del café Colombiano,” Mundo FESC, vol. 13, no. S1, pp. 258–272, Dec. 2023, doi: 10.61799/2216-0388.1499.
[32] C. Bernal, Metodología de la investigación, 3rd ed. 2014.
[33] C. C. Holt, “Forecasting seasonals and trends by exponentially weighted moving averages,” Int J Forecast, vol. 20, no. 1, pp. 5–10, Jan. 2004, doi: 10.1016/j.ijforecast.2003.09.015.
[34] P. R. Winters, “Forecasting Sales by Exponentially Weighted Moving Averages,” Manage Sci, vol. 6, pp. 324–342, 1960, Accessed: Sep. 07, 2025. [Online]. Available: http://www.jstor.org/stable/2627346
[35] G. Box, G. Jenkins, G. Reinsel, and G. Ljung, Time Series Analysis: Forecasting and Control. Wiley, 2016.
[36] J. D. Velásquez, C. Zambrano, and L. Vélez, “ARNN: un paquete para la predicción de series de tiempo usando redes neuronales autorregresivas,” Revista Avances en Sistemas e Informática, vol. 8, no. 2, pp. 177–181, 2011. URL: https://dialnet.unirioja.es/servlet/articulo?codigo=5247007
[37] C. Chen and L.-M. Liu, “Joint Estimation of Model Parameters and Outlier Effects in Time Series,” J Am Stat Assoc, vol. 88, no. 421, pp. 284–297, Mar. 1993, doi: 10.1080/01621459.1993.10594321.
Published
Issue
Section
License
Copyright (c) 2026 Mundo FESC Journal
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
