An Effective Computational Model for Bankruptcy Prediction Using Kernel Extreme Learning Machine Approach

Bankruptcy prediction is becoming more and more important issue in financial decision-making. It is essential to make the companies prevent from bankruptcy through building effective corporate bankruptcy prediction model in time. This study proposes an effective bankruptcy prediction model based on the kernel extreme learning machine (KELM). A two-step grid search strategy which integrates the coarse search with the fine search is adopted to train KELM. The resultant bankruptcy prediction model is compared with other five competitive methods including support vector machines, extreme learning machine, random forest, particle swarm optimization enhanced fuzzy k-nearest neighbor and Logit model on the real life dataset via 10-fold cross validation analysis. The obtained results clearly confirm the superiority of the developed model in terms of classification accuracy, Type I error, Type II error and area under the receiver operating characteristic curve (AUC) criterion. Promisingly, the proposed KELM can serve as a new candidate of powerful early warning systems for bankruptcy prediction with excellent performance.