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.

中文翻译：

---

基于边界SMOTE的深度学习方法进行破产预测

破产预测的不平衡分类被认为是金融机构中最重要的主题之一。在这种情况下，已经提出了各种统计和人工智能方法。近年来，深度学习算法正逐渐兴起，并且被广泛用于构建预测和分类模型。为此，我们提出了一种新颖的基于深度学习的方法，称为BSM-SAES。这种方法结合了基于Softmax分类器的边界综合少数族裔过采样技术（BSM）和堆叠式自动编码器（SAE）。目的是开发一种准确可靠的破产预测模型，其中包括特征提取过程。为了评估我们提出的模型的分类性能，k-最近邻，决策树，支持向量机，以及使用了人工神经网络C5.0作为机器学习方法。我们对波兰不平衡数据集评估了我们提出的方法。与其他有关预测和分类公司财务状况的机器学习模型相比，获得的结果证实了我们提出的模型的效率。