Evolution of the SME loan portfolio in Ecuador: a Holt-Winters approach and the Extreme Learning Machine network

• Armando José Urdaneta Montiel

  Universidad Metropolitana del Ecuador Machala, Ecuador.

  https://orcid.org/0000-0002-9825-9453

• Ángel Alberto Zambrano Morales

  Universidad Metropolitana del Ecuador Machala, Ecuador

  https://orcid.org/0000-0002-7897-7327

• Leopoldo Wenceslao Condori Cari

  Universidad Andina Néstor Cáceres Velásquez Juliaca, Perú.

  https://orcid.org/0000-0003-2372-6720

• José Roberto Morales Vergara

  Universidad de Guayaquil. Guayaquil, Ecuador.

  https://orcid.org/0000-0001-7814-3624

Esta investigación, de enfoque mixto, se basó en la predicción de la evolución de la cartera de créditos a PYMES en Ecuador. Se utilizó el modelo Holt-Winters y la red Extreme Learning Machine, que combinan modelos econométricos y redes neuronales, acompañados del análisis geoespacial a nivel de provincias. El modelo presentó ajuste óptimo de los datos reales, comprende eficazmente el 93 % de la variabilidad de estos, muestra un eficiente pronóstico y rendimiento ligeramente superior sobre otros modelos analizados. Este resultado es crucial para la toma de decisiones y la planificación de los recursos financieros destinados a las PYMES ecuatorianas.

Acosta, G. (2019). Responsabilidad social empresarial: inclusión financiera en el sistema bancario privado ecuatoriano. Visión de Futuro, 23(1), 1-11.

Ahmar, A., Singh, P., & Thanh, N. (2021). Prediction of BRIC Stock Price Using ARIMA, SutteARIMA, and Holt-Winters. Tech Science Press, 70(1), 523-534. doi:10.32604/cmc.2022.017068

Almazrouee, A., Almeshal, A., Abdulrahman, A., Alenezi, M. R., & Alhajeri, S. (2020). Long-Term Forecasting of Electrical Loads in Kuwait Using Prophet and Holt–Winters Models. Applied Sciences, 1-17.

Álvarez, J., Cabrera, P., & Jácome, H. (2023). Territorial inequalities in financial inclusion: A comparative study between private banks and credit unions. Socio-Economic Planning Sciences.

Amadasun, D., & Mutezo, A. (2022). Infuence of access to fnance on the competitive growth of SMEs in Lesotho. Journal of Innovation and Entrepreneurship, 1-20.

Anzules, W., & Novillo, S. (2023). Innovation Capacity, Entrepreneurial Orientation, and Flexibility: An Analysis from Industrial SMEs in Ecuador. Sustainability, 1-24.

Apichatibutarapong, S. (2015). Business forecasting technique on mobile devices by using R-Programming. Procedia - Social and Behavioral Sciences, 197, 1377-1382. doi: doi: 10.1016/j.sbspro.2015.07.081

Atoyebi, S. B., Olayiwola, M. F., Oladapo, J. O., & Oladapo, D. I. (2023). Forecasting Currency in Circulation in Nigeria Using Holt-Winters Exponential Smoothing Method. South Asian Journal of Social Studies and Economics, 20(1), 25-41. doi:10.9734/SAJSSE/2023/v20i1689

Attar, M. A. (2021). Growth, distribution and dynamic inefficiency in Turkey: An analysis of the naïve neoclassical theory of capital. Structural Change and Economic Dynamics, 59, 20-30.

Bacuilima, E., Morocho, J., Aguirre, J., Coronel, K., & Mora, P. (2023). Financing Ecuadorian Social Enterprises: What Is the Role of Impact Investment? Sustainability, 1-19.

Bairagi, V., & Munot, M. (2019). Research Methodology: A Practical and Scientific Approach. Boca Ratón, Florida, Estados Unidos: CRC Press.

Coaquira, M., Tudela, J., & Jiménez, M. (2023). Evaluación comparativa regional: índice sintético de desarrollo regional (IDR) para Perú. Revista Desarrollo y Sociedad, 109-157.

Deina, C., Prates, M., Alves, C., Martins, M., Trojan, F., Stevan, S., & Siqueira, H. (2021). A methodology for coffee price forecasting based on extreme learning machines. Information Processing in Agriculture(9), 556-565. doi:https://doi.org/10.1016/j.inpa.2021.07.003

Díaz, R., Bravo, L., Alatorre, L., & Sánchez, E. (2014). Análisis geoespacial de la interacción entre el uso de suelo y de agua en el área peri-urbana de Cuauhtémoc, Chihuahua. Un estudio socioambiental en el norte de México. Investigaciones Geográficas, Boletín del Instituto de Geografía, UNAMISSN 0188-4611(83), 116-130. doi:10.14350/rig.32694

Dritsaki, M., & Dritsaki, C. (2021). Comparison of the Holt-Winters Exponential Smoothing Method with ARIMA Models: Forecasting of GDP per Capita in Five Balkan Countries Members of European Union (EU) Post COVID. Scientific Research Publishing Inc, 1972-1998.

Feijó, N., Ceular, N., & Navajas, V. (2023). Behavioral Patterns That Influence the Financing Choice Models of Small Enterprises in Ecuador through Latent Class Analysis. Sustainability, 15 , 1-17. doi:https://doi.org/10.3390/su15086790

Hidayat, A., & Darmawan, P. (2023). ARIMA Model and Holt Winters Seasonal Smoothing Accuracy for Stock Price Prediction. Journal of Actuarial, Finance and Risk Management (JAFRM), 2(1), 10-19. doi: https://doi.org/10.25077/jafrm.2.1.10-19

Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, Volume 70, Issues 1–3, 489-501. doi:https://doi.org/10.1016/j.neucom.2005.12.126

Karadžić, V., & Pejović, B. (2021). Inflation forecasting in the Western Balkans and EU: A comparison of Holt-Winters, ARIMA and NNAR models. Amfiteatru Economic, 23(57), 517-532.

Li, H., Bai, J., & Li, Y. (2019). ). Anovel secondary decomposition learning paradigm with kernel extreme learning machine for multi-step forecasting of container throughput. Physical A: Statistical Mechanics and its Applications, 534, 122025. doi:https://doi.org/10.1016/j.physa.2019.122025.

Lima, S., Gonçalves, M., & Costa, M. (2019). Time series forecasting using Holt-Winters exponential smoothing: An application to economic data. Proceedings of the International Conference of Computational Methods in Sciences and Engineering 2019 (ICCMSE-2019). Published by AIP Publishing. 978-0-7354-1933-9. doi:doi.org/10.1063/1.5137999

Liu, C., Sun, B., Zhang, C., & Li, F. (2020). A hybrid prediction model for residential electricity consumption using holt- winters and extreme learning machine. Applied Energy, 275, 1-15.

Longley, P., Goodchild, M., Maguire, D., & Rhind, D. (2015). Geographic Information Science and Systems. United State of America: WILEY.

Makridakis, S., Spiliotis, E., & & Assimakopoulos, V. (2020). The M4 Competition: 100,000 time series and 61 forecasting methods. International Journal of Forecasting, 54-74. doi:https://doi.org/10.1016/j.ijforecast.2019.04.014

Mejía, E., & Gonzales, S. (2019). Predicción del consumo de energía eléctrica residencial de la Región Cajamarca mediante modelos Holt -Winters. Ingeniería Energética, 40(3), 181-191.

Naim, I., Mahara, T., & Rahman, A. (2018). Effective short-term forecasting for daily time series with complex seasonal patterns. Procedia Computer Science, 132, 1832-1841. doi:. https://doi.org/10.1016/j.procs.2018.05.136

Pang, S., Hou, X., & Xia, L. (2021). Borrowers' credit quality scoring model and applications, with default discriminant analysis based on the extreme learning machine. Technological Forecasting & Social Change, 165. doi:https://doi.org/10.1016/j.te

Pleños, M. (2022). Time Series Forecasting Using Holt-Winters Exponential Smoothing: Application to Abaca Fiber Data. Problems of World Agriculture. Scientific Journal Warsaw University of Life Sciences, 22(2), 17-29. doi:10.22630/PRS.2022.22.2.6

Proaño, B., & Feria, J. (2022). Are Ecuadorian banks enough technically efficient for growth? A clinical study. WILEY, 1-19.

Sokolov-Mladenović, S., Milovančević, M., & Mladenović, I. (2016). Sokolov-Mladenović Economic growth forecasting by artificial neural network with extreme learning machine based on trade, import and export parameters. Sokolov-Mladenović, S., Milovančević, M., & Mladenović, I. (2016). Economic growth forecasting by artificial neural network with extreme Computers in Human Behavior(65), 43-45. doi:10.1016/j.chb.2016.08.014

Sulaiman, A., & Juarna, A. (2021). PERAMALAN TINGKAT PENGANGGURAN DI INDONESIA MENGGUNAKAN METODE TIME SERIES DENGAN MODEL ARIMA DAN HOLT-WINTERS. Jurnal Ilmiah Informatika Komputer, 26(1), 13-28.

Urdaneta, A. J., & Borgucci, E. V. (2021). Economías de aglomeración y externalidades negativas en Ecuador, periodo 2007-2017. Cuadernos de Economía, 40(82), 165-191.

Wang, J., Athanasopoulos, G., Hyndman, R. J., & Wang, S. (2018). Crude oil price forecasting based on internet concern using an extreme learning machine. International Journal of Forecasting., 34(4), 665-677. doi:https://doi.org/10.1016/j.ijforecast.2018.03.00

Winters, P. (1960). Forecasting Sales by Exponentially Weighted Moving Averages. Management Science, 6(3), 324-342.

Zhou, W., Tao, H., & Jiang, H. (2022). Application of a novel optimized fractional grey Holt-Winters model in energy forecasting. Sustainability, 14(5), 1-18. doi:https://doi.org/10.3390/su14053118

• PDF

Derechos de autor 2025 Encuentros. Revista de Ciencias Humanas, Teoría Social y Pensamiento Crítico.

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.