Calculando el riesgo de insolvencia, de los métodos tradicionales a las redes neuronales artificiales. Una revisión de literatura

• Ludeña Dávila, Maryann Katherine ^[1] ; Tonon Ordóñez, Luis Bernardo ^[1]
  1. [1] Universidad del Azuay

     Universidad del Azuay

     Cuenca, Ecuador

     
• Localización: INNOVA Research Journal, ISSN-e 2477-9024, Vol. 6, Nº. 3, 2021 (Ejemplar dedicado a: (Septiembre -Diciembre, 2021)), págs. 270-287
• Idioma: español
• DOI: 10.33890/innova.v6.n3.2021.1790
• Títulos paralelos:
  • Calculating the risk of insolvency, from traditional methods to artificial neural networks. A literature review
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    En la administración financiera de toda organización el cálculo del riesgo de insolvencia se ha convertido en un parámetro importante, buscando anticiparse a la eventualidad de llegar a tener un problema económico y generar insolvencia. El objetivo de este trabajo es determinar si en el cálculo del riesgo de insolvencia, el uso de redes neuronales artificiales genera mejores resultados que las metodologías tradicionales, buscando las principales características dentro de las aplicaciones realizadas por distintos autores a través del tiempo. De esta manera se observan las principales variables que pueden evidenciar que la aplicación de la metodología de redes neuronales facilita el cálculo del riesgo de insolvencia.  A través de la revisión bibliográfica, en el período 1992-2021, con el uso del método analítico-sintético se puede evidenciar que el modelo expuesto es considerado como eficiente según sus resultados, con ajustes que, en la mayoría de los casos expuestos, superan el 80% de eficacia. Los resultados encontrados permitieron concluir que la estructura básica de una red neuronal viene dada por tres capas: una de entrada, una de salida y una oculta. Sin embargo, el número de nodos es el que varía en cada una de las aplicaciones realizadas por los distintos autores, dado que los mismos representan a las variables, en este caso indicadores financieros más relevantes según la aplicación planteada. Finalmente se logró evidenciar cuáles son los indicadores financieros más usados en las distintas aplicaciones de redes neuronales. Todo indica que las redes neuronales generan resultados más efectivos que los métodos tradicionales. 

  • English

    In the financial management of any organization, the calculation of the risk of insolvency has become an important parameter, seeking to anticipate the eventuality of having an economic problem and generating insolvency. The objective of this work is to compare the classical methodologies and the artificial neural networks applied to calculate the risk of insolvency, looking for the main characteristics within the applications carried out by different authors over time. In this way, the main variables that can show that the application of the neural network methodology facilitates the calculation of the risk of insolvency are observed. Through the bibliographic review, between the years 1992-2021, with the use of the analytical-synthetic method, it can be seen that the exposed model is considered efficient according to its results, with adjustments that, in most of the exposed cases, exceed 80% efficiency. The results found allowed us to conclude that the basic structure of a neural network is given by three layers: an input layer, an output layer and a hidden layer. However, the number of nodes varies in each of the applications carried out by the different authors, since they represent the variables, in this case the most relevant financial indicators according to the proposed application. Finally, it was possible to show which are the most used financial indicators in the different neural network applications.

• Referencias bibliográficas
  • Abdelwahed, T., & Amir, E. (2005). New evolutionary bankruptcy forecasting model based on genetic algorithms and neural networks. 17th...
  • Abedin, M., Guotai, C., Colombage, S., & Fahmida-E-Moula. (2018). Credit default prediction using a support vector machine and a probabilistic...
  • Alaka, H., Oyedele, L., Owolabi, H., Oyedele, A., Akinade, O., Bilal, M., & Ajayi, S. (2017). Critical factors for insolvency prediction:...
  • Alam, P., Booth, D., Lee, K., & Thordarson, T. (2000). The use of fuzzy clustering algorithm and self-organizing neural networks for identifying...
  • Alfaro, E., García, N., Gámez, M., & Elizondo, D. (2008). Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks....
  • Allen, F., & Gale, D. (2004). Competition and Financial Stability. Journal of Money, Credit, and Banking, 36(3).
  • Altman, E. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, 23, 589-609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
  • Altman, E. (1983). Corporate financial distress: A complete guide to predicting avoiding and dealing with failedcy. New York: John Wiley and...
  • Altman, E. (2001). Bankruptcy, Credit Risk and High Yield Junk Bonds. New York: Blackwell Publishing.
  • Altman, E., Marco, G., & Varetto, F. (1994). Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks...
  • Aminian, F., Suarez, E., Aminiam , M., & Walz, D. (2006). Forecasting economic data with neural networks. Computational Economics, 28(1),...
  • Atiya, A. (2001). Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on neural networks,...
  • Back, B., Oosterom, G., Sere, K., & Van Wezel, M. (1994). A comparative study of neural networks in bankruptcy prediction. Proc. Conf....
  • Baek, J., & Cho, S. (2003). Bankruptcy prediction for credit risk using an auto-associative neural network in Korean firms. In 2003 IEEE...
  • Barboza, F., Kimura, H., & Altman, E. (2017). Machine learning models and bankruptcy prediction. Expert Systems with Applications, 83,...
  • Barrow, D., & Crone, S. (2016). Cross-validation aggregation for combining autoregressive neural network forecasts. International Journal...
  • Beaver, W. (1966). Financial Ratios As Predictors of Failure. Journal of Accounting Research, 4, 71-111. https://doi.org/10.2307/2490171
  • Bešlić, D., Jakšić, D., Bešlić, I., & Andrić, M. (2018). Insolvency prediction model of the company: the case of the Republic of Serbia....
  • Binner, J., Gazely, A., Chen, S., & Chie, B. (2004). Financial innovation and Divisia money in Taiwan: Comparative evidence from neural...
  • Boyacioglu, M., Kara, Y., & Baykan, Ö. (2009). Predicting bank financial failures using neural networks, support vector machines and multivariate...
  • Brigham, E., & Ehrhardt, M. (2007). Financial Management: Theory and Practice (14 ed.). South-Western Cengage Learning.
  • Brockett, P., Cooper, W., Golden, L., & Pitaktong, U. (1994). A neural network method for obtaining an early warning of insurer insolvency....
  • Caporale, G., Cerrato, M., & Zhang, X. (2017). Analysing the determinants of insolvency risk for general insurance firms in the UK. Journal...
  • Charalambous, C., Charitou, A., & Kaourou, F. (2000). Comparative analysis of artificial neural network models: Application in bankruptcy...
  • Conti, D., Simó, C., & Rodríguez, A. (2005). Teoría de carteras de inversión para la diversificación del riesgo: enfoque clásico y uso...
  • Corazza, M., De March, D., & di Tollo, G. (2021). Design of adaptive Elman networks for credit risk assessment. Quantitative Finance,...
  • Del Carpio Gallegos, J. (2005). Las Redes Neuronales en las Finanzas. Revista de la Facultad de Ingeniería Industrial, 8(2), 28-32. http://200.62.146.34/bitstream/handle/123456789/1936/industrial_data04v8n2_2005.pdf?sequence=1&isAllowed=y
  • Dinca, G., Baba, M., Dinca, M., Dauti, B., & Deari, F. (2017). Insolvency risk prediction using the logit and logistic models: Some evidences...
  • Do Prado, J., De Melo, F., Carvalho, G., & Ribeiro, A. (2019). Analysis of credit risk faced by public companiesin Brazil: an approach...
  • Du Jardin, P. (2010). Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques...
  • Ecer, F. (2013). Comparing the bank failure prediction performance of neural networks and support vector machines: The Turkish case. Economic...
  • FitzPatrick, P. (1932). Average Ratios of Twenty Representative Industrial Failures. The Certified Public Accountant, 13-18.
  • Giacosa, E., Halili, E., Mazzoleni, A., Teodori, C., & Veneziani, M. (2016). Re-estimation of company insolvency prediction models: survey...
  • Hensher, D., Jones, S., & Greene, W. (2007). An error component logit analysis of corporate bankruptcy and insolvency risk in Australia....
  • Khediri, K., Charfeddine, L., & Yousseef, S. (2015). Islamic versus conventional banks in the GCC countries: A comparative study using...
  • Kim, S. (2011). Prediction of hotel bankruptcy using support vector machine, artificial neural network, logistic regression, and multivariate...
  • Kumar, P., & Ravi, V. (2007). Bankruptcy prediction in banks and firms via statistical and intelligent techniques–A review. European journal...
  • Lahmiri, S., & Bekiros, S. (2019). Can machine learning approaches predict corporate bankruptcy? Evidence from a qualitative experimental...
  • Lepetit, L., & Strobel, F. (2015). Bank Insolvency Risk and Z-Score Measures: A Refinement. Finance Research Letters, 13, 214-224. http://doi.org/10.1016/j.frl.2015.01.001
  • Leshno, M., & Spector, Y. (1996). Neural network prediction analysis: The bankruptcy case. Neurocomputing, 10(2), 125-147. https://doi.org/10.1016/0925-2312(94)00060-3
  • Mohammadian, M. (2012). Artificial intelligence applications for risk analysis, risk prediction and decision making in disaster recovery planning....
  • Nadali, L., Corazza, M., Parpinel, F., & Pizzi, C. (2020). Recurrent ANNs for Failure Predictions on Large Datasets of Italian SMEs. In...
  • Nasir, M., John, R., Bennett, S., & Russell, D. (2000). Predicting corporate bankruptcy using modular neural networks. In Proceedings...
  • Obermann, L., & Waack, S. (2015). Demonstrating non-inferiority of easy interpretable methods for insolvency prediction. Expert Systems...
  • Odom, M., & Sharda, R. (1990). A neural network model for bankruptcy prediction. In 1990 IJCNN International Joint Conference on neural...
  • Ohlson, J. (1980). Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal of Accounting Research, 18(1). https://doi.org/10.2307/2490395
  • Orellana, I., Tonon, L., Reyes, M., Pinos, L., & Cevallos, E. (2020). Riesgos financieros en el sector manufacturero del Ecuador (1.a...
  • Rodríguez, M., Piñeiro, C., & De Llano, P. (2014). Determinación del riesgo de fracaso financiero mediante la utilización de modelos paramétricos,...
  • Romani, G., Bravo, A., Aroca, P., Aguirre, N., Vega, P., y Carrazana, J. (2002). Modelos de clasificación y predicción de quiebra de empresas:...
  • Rubin, P. (1990). A comparison of linear programming and parametric approaches to the two‐group discriminant problem. Decision Sciences, 21(2),...
  • Rustam, Z., & Yaurita, F. (2018). Insolvency Prediction in Insurance Companies Using Support Vector Machines and Fuzzy Kernel C-Means....
  • Taffler, R. (1983). The assessment of company solvency and performance using a statistical model. Accounting and Business Research, 13(52),...
  • Tay, F., & Shen, L. (2002). Economic and financial prediction using rough sets model. European Journal of Operational Research, 141(3),...
  • Thakor, A. (2018). Post-crisis regulatory reform in banking: Address insolvency risk, not illiquidity! Journal of Financial Stability, 37,...
  • Tseng, F., & Hu, Y. (2010). Comparing four bankruptcy prediction models: Logit, quadratic interval logit, neural and fuzzy neural networks....
  • Valdes, M., Aleaga, A., y Vidal, G. (2014). Redes neuronales artificiales en la predicción de insolvencia. Un cambio de paradigma ante recetas...
  • Wilson, R., & Sharda, R. (1994). Bankruptcy prediction using neural networks. Decision support systems, 11(5), 545-557. https://doi.org/10.1016/0167-9236(94)90024-8
  • Zhang, G., Hu, M., Patuwo, B., & Indro, D. (1999). Artificial neural networks in bankruptcy prediction: General framework and cross-validation...