Comparing the Performance of Deep Learning Methods to Predict Companies' Financial Failure

This work was supported in part by the Ministerio de Ciencia, Innovacion y Universidades under Project RTI2018-102002-A-I00, in part by the Ministerio de Economia y Competitividad under Project TIN2017-85727-C4-2-P and Project PID2020-115570GB-C22, in part by the Fondo Europeo de Desarrollo Regional (FEDER) and Junta de Andalucia under Project B-TIC-402-UGR18, and in part by the Junta de Andalucia under Project P18-RT-4830.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.Ministerio de Ciencia, Innovacion y Universidades RTI2018-102002-A-I00Spanish Government TIN2017-85727-C4-2-P PID2020-115570GB-C22European Commission B-TIC-402-UGR18Junta de Andalucia B-TIC-402-UGR18 P18-RT-483