Optimización de hiperparámetros de regresión del proceso gaussiano para predecir problemas financieros

Contenido principal del artículo

Resumen

La predicción de las dificultades financieras se ha convertido en uno de los temas más importantes en el área contable y financiera debido a su correlación significativa con el desarrollo de la ciencia y la tecnología. El objetivo principal de este trabajo es predecir la dificultad financiera con base en la Regresión de Procesos Gaussianos (GPR) y luego comparar los resultados de este modelo con los resultados de otros modelos de aprendizaje profundo (SVM, LR, LD, DT, KNN). El análisis se basa en un conjunto de datos de 352 empresas extraídos de la base de datos de Kaggle. En cuanto a los predictores, se utilizaron 83 ratios financieros. El estudio concluyó que el uso de la GPR logra resultados muy relevantes. Además, superó al resto de los modelos de aprendizaje profundo y logró el primer lugar por igual con el modelo SVM con una precisión de clasificación del 81 %. Los resultados contribuyen al mantenimiento del sistema integrado y a la prosperidad de la economía del país, a la predicción de las dificultades financieras de las empresas y, por lo tanto, a la posible prevención de perturbaciones del sistema en cuestión.

Detalles del artículo

Sección
Artículos destinados a la sección miscelánea
Biografía del autor/a

Jakub Horak

DOCTORADO   Enlace GOOGLE SCHOLAR https://scholar.google.com/citations?user=_qBCya4AAAAJ&hl=cs   Enlace de perfil ORCID https://orcid.org/0000-0001-6364-9745   INDICE H: 11

Referencias

Asante-Okyere, S., Shen, C., Ziggah, Y. Y., Rulegeya, M. M. y Zhu, X. 2018. Investigating the predictive performance of Gaussian process regression in evaluating reservoir porosity and permeability. Energies, 11.

https://doi.org/10.3390/en11123261

Bonello, J., Brédart, X. y Vella, V. 2018. Machine learning models for predicting financial distress. Journal of Research in Economics, 2, 174-185. https://doi.org/10.24954/JORE.2018.22

Chen, S. y Shen, Z. D. 2020. Financial distress prediction using hybrid machine learning techniques. Asian Journal of Economics, Business and Accounting, 16, 1-12. https://doi.org/10.9734/ajeba/2020/v16i230231

Chen, S. D. y Jhuang, S. 2018. Financial distress prediction using data mining techniques. ICIC Express Letters, Part B: Applications, 9(2), 131-136. https://bit.ly/3qH5eHc

Chen, W.-S. y Du, Y.-K. 2009. Using neural networks and data mining techniques for the financial distress prediction model. Expert Systems with Applications, 36(2), 4075-4086.

https://doi.org/10.1016/j.eswa.2008.03.020

Costa, M., Lisboa, I. y Gameiro, A. 2022. Is the financial report quality important in the default prediction? SME Portuguese Construction Sector Evidence. Risks, 10(5).

https://doi.org/10.3390/risks10050098

Ferkousl, K., Chellalil, F., Kouzoul, A. y Bekkar, B. 2021. Wavelet-Gaussian process regression model for forecasting daily solar radiation in the Saharan climate. Clean Energy, 5(2), 316-328. https://doi.org/10.1093/ce/zkab012

Gavurova, B., Belas, J., Bilan, Y. y Horak, J. 2020. Study of legislative and administrative obstacles to SMEs business in the Czech Republic and Slovakia. Oeconomia Copernicana, 11(4), 689-719. https://doi.org/10.24136/OC.2020.028

Gregova, E., Valaskova, K., Adamko, P., Tumpach, M. y Jaros, J. 2020. Predicting financial distress of slovak enterprises: comparison of selected traditional and learning algorithms methods. Sustainability, 12(10).

https://doi.org/10.3390/su12103954

Hamoudi, Y., Amimeur, H., Aouzellag, D., Abdolraso, M. G. M. y Ustun, T. S. 2023. Hyperparameter bayesian optimization of Gaussian process regression applied in speed-sensorless predictive torque control of an autonomous wind energy conversion system. Energies, 16(12). https://doi.org/10.3390/en16124738

Hantono, H. (2019). Predicting financial distress using Altman score, Grover score, Springate score, Zmijewski score (case study on consumer goods company). Accountability, 8(1), 1-16.

https://doi.org/10.32400/ja.23354.8.1.2019.1-16

Herfurth, H. 2020. Gaussian process regression in computational finance. Project Report, Uppsala University, 1-29. https://bit.ly/3KGoUSk

Horak, J., Vrbka, J. y Suler, P. 2020. Support vector machine methods and artificial neural networks used for the development of bankruptcy prediction models and their comparison. Journal of Risk and Financial Management, 13(3). https://doi.org/10.3390/jrfm13030060

Jan, C. l. 2021. Financial information asymmetry: using deep learning algorithms to predict financial distress. Symmetry, 13(3). https://doi.org/10.3390/sym13030443

Jeong, J. y Kim, C. 2022. Comparison of machine learning approaches for medium-to-long-term financial distress predictions in the construction industry. Buildings, 12(10). https://doi.org/10.3390/buildings12101759

Kliestik, T., Vrbka, J. y Rowland, Z. 2018. Bankruptcy prediction in Visegrad group countries using multiple discriminant analysis. Equilibrium-Quarterly Journal of Economics and Economic Policy, 13(3), 569-593.

https://doi.org/10.24136/eq.2018.028

Krulicky, T. y Horak, J. 2021. Business performance and financial health assessment through Artificial Intelligence. Ekonomicko - manažerské spektrum, 15(2), 38-51.

Liew, K. F., Lam, W. S. y Lam, W. H. 2023. Financial distress analysis of technology companies using grover model. Computer Sciences & Mathematics Forum, 7(1).

https://doi.org/10.3390/IOCMA2023-14405

Liu, Y., Chen, K., Kumar, A. y Patnaik, P. 2023. Principles of machine learning and its application to thermal barrier coatings. Coatings, 13(7). https://doi.org/10.3390/coatings13071140

Paule-Vianez, J. 2019. Bayesian networks to predict financial distress in spanish banking. Revista Electrónica de Comunicaciones y Trabajos de ASEPUMA, 20, 131-152. https://doi.org/10.24309/recta.2019.20.2.02

Qu, Y., Quan, P., Lei, M. y Shi, Y. 2019. Review of bankruptcy prediction using machine learning and deep learning techniques. Procedia Computer Science, 162, 895-899.

https://doi.org/10.1016/j.procs.2019.12.065

Rahman, M., Sa, C. L. y Masud. M. A. K. 2021. Predicting firms’ financial distress: an empirical analysis using the F-Score Model. Journal of Risk and Management, 14(5).

https://doi.org/10.3390/jrfm14050199

Shi, Y. y Li, X. 2019. An overview of bankruptcy prediction models for corporate firms: A systematic literature review. Intangible Capital Journal, 15(2), 1866-1875. https://doi.org/10.3926/ic.1354

Taki, M., Rohani, A., Soheili-Fard, F. y Abdeshahi, A. 2018. Assessment of energy consumption and modeling of output energy for wheat production by neural network (MLP and RBF) and Gaussian process regression (GPR) models. Journal of Cleaner Production, 172, 3028-3041. https://doi.org/10.1016/j.jclepro.2017.11.107

Vochozka, M., Vrbka, J. y Suler, P. 2020. Bankruptcy or success? The effective prediction of a company’s financial development using LSTM. Sustainability, 12(18).

https://doi.org/10.3390/su12187529

Wang, S., Gong, J., Gao, H., Liu, W. y Feng, Z. 2023. Gaussian process regression and cooperation search algorithm for forecasting nonstationary runoff time series. Water, 15(11). https://doi.org/10.3390/w15112111

Yang, Z., Li, X., Yao, X., Sun, J. y Shan, T. 2023. Gaussian Process Gaussian Mixture PHD filter for 3D multiple extended target Tracking. Remote Sensing, 15(13).

https://doi.org/10.3390/rs15133224

Zhou, T., Song, Z. y Sundmacher, K. 2019. Big data creates new opportunities for materials research: a review on methods and applications of machine learning for materials design. Engineering, 5, 1017-1026.

https://doi.org/10.1016/j.eng.2019.02.011