Bankruptcy Prediction Using Deep Learning Approach Based on Borderline SMOTE
- PDF / 1,484,205 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 42 Downloads / 264 Views
Bankruptcy Prediction Using Deep Learning Approach Based on Borderline SMOTE Salima Smiti 1 & Makram Soui 2
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Imbalanced classification on bankruptcy prediction is considered as one of the most important topics in financial institutions. In this context, various statistical and artificial intelligence methods have been proposed. Recently, deep learning algorithms are experiencing a resurgence of interest, and are widely used to build a prediction and classification models. To this end, we propose a novel deep learning-based approach called BSM-SAES. This approach combines Borderline Synthetic Minority oversampling technique (BSM) and Stacked AutoEncoder (SAE) based on the Softmax classifier. The aim is to develop an accurate and reliable bankruptcy prediction model which includes the features extraction process. To assess the classification performance of our proposed model, k- nearest neighbor, decision tree, support vector machine, and artificial neural network, C5.0 that are machine learning methods, are applied. We evaluate our proposed approach on the Polish imbalanced datasets. The obtained results confirm the efficiency of our proposed model compared to other machine learning models regarding predicting and classifying the financial status of a firm. Keywords Bankruptcy prediction . Deep learning . Stacked autoencoder . Borderline SMOTE . Imbalanced dataset
1 Introduction In the current economic situation, bankruptcy prediction has become an important task that provides timely alerts to decision makers of the company. The ultimate aim of this prediction is to confirm economic stability and to enhance the efficiency of the commercial credit allocation. In addition, the number of company bankruptcies is crucial to a country’s economy, and it can be considered as an indicator of economic development (Van Gestel et al. n.d.). Furthermore, the economic, social costs and high number of companies that faced bankruptcies have let experts to better understand the bankruptcy risk (McKee and Lensberg 2002). Hence, the risk of bankruptcy can influence the country's
* Salima Smiti [email protected] Makram Soui [email protected] 1
National School of Computer Science, University of Manouba, Manouba, Tunisia
2
College of Computing and Informatics, Saudi Electronic University, Arabie Saoudite, Riyadh, Saudi Arabia
economy. Thus, the bankruptcy prediction has gained an increasingly important role in the economy and society since it has an essential impact on the profitability of financial institutions. The aim is to evaluate a firm’s financial situation and its future perspectives (Constand and Yazdipour 2011). Indeed, it has become more significant since the advent of the Basel II requirement. This consent highlights its importance for an accurate decisionmaking model. Besides, Basel II permits banks to assess the company’s risk of bankruptcy based on its its own internal models, the probability of default, and the capital needed to fa
Data Loading...
