A Back Propagation Neural Network Model with the Synthetic Minority Over-Sampling Technique for Construction Company Bankruptcy Prediction

Improving model accuracy is one of the most frequently addressed issues in bankruptcy prediction. Several previous studies employed artificial neural networks (ANNs) to improve the accuracy at which construction company bankruptcy can be predicted. However, most of these studies use the sample-matching technique and all of the available company quarters or company years in the dataset, resulting in sample selection biases and between-class imbalances. This study integrates a back propagation neural network (BPNN) with the synthetic minority over-sampling technique (SMOTE) and the use of all of the available company-year samples during the sample period to improve the accuracy at which bankruptcy in construction companies can be predicted. In addition to eliminating sample selection biases during the sample matching and between-class imbalance, these methods also achieve the high accuracy rates. Furthermore, the approach used in this study shows optimal over-sampling times, neurons of the hidden layer, and learning rate, all of which are major parameters in the BPNN and SMOTE-BPNN models. The traditional BPNN model is provided as a benchmark for evaluating the predictive abilities of the SMOTE-BPNN model. The empirical results of this paper show that the SMOTE-BPNN model outperforms the traditional BPNN