Comparing the Performance of Deep Learning Methods to Predict Companies' Financial Failure
Metadatos
Mostrar el registro completo del ítemAutor
Aljawazneh, Huthaifa Riyad; Mora García, Antonio Miguel; García Sánchez, Pablo; Castillo Valdivieso, Pedro ÁngelEditorial
IEEE
Materia
Economic forecasting Classification algorithms Machine learning Deep learning Data balancing
Fecha
2021-06-29Referencia bibliográfica
H. Aljawazneh... [et al.]. "Comparing the Performance of Deep Learning Methods to Predict Companies’ Financial Failure," in IEEE Access, vol. 9, pp. 97010-97038, 2021, doi: [10.1109/ACCESS.2021.3093461]
Patrocinador
Ministerio de Ciencia, Innovacion y Universidades RTI2018-102002-A-I00; Spanish Government TIN2017-85727-C4-2-P PID2020-115570GB-C22; European Commission B-TIC-402-UGR18; Junta de Andalucia B-TIC-402-UGR18 P18-RT-4830Resumen
One of the most crucial problems in the eld of business is nancial forecasting. Many
companies are interested in forecasting their incoming nancial status in order to adapt to the current
nancial and business environment to avoid bankruptcy. In this work, due to the effectiveness of Deep
Learning methods with respect to classi cation tasks, we compare the performance of three well-known
Deep Learning methods (Long-Short Term Memory, Deep Belief Network and Multilayer Perceptron model
of 6 layers) with three bagging ensemble classi ers (Random Forest, Support Vector Machine and K-Nearest
Neighbor) and two boosting ensemble classi ers (Adaptive Boosting and Extreme Gradient Boosting) in
companies' nancial failure prediction. Because of the inherent nature of the problem addressed, three
extremely imbalanced datasets of Spanish, Taiwanese and Polish companies' data have been considered in
this study. Thus, ve oversampling balancing techniques, two hybrid balancing techniques (oversamplingundersampling)
and one clustering-based balancing technique have been applied to avoid data inconsistency
problem. Considering the real nancial data complexity level and type, the results show that the Multilayer
Perceptron model of 6 layers, in conjunction with SMOTE-ENN balancing method, yielded the best
performance according to the accuracy, recall and type II error metrics. In addition, Long-Short Term
Memory and ensemble methods obtained also very good results, outperforming several classi ers used in
previous studies with the same datasets.