Evaluation of Cost-Sensitive Learning Models in Forecasting Business Failure of Capital Market Firms

Classifying imbalanced data is a well-known challenge in machine learning. One of the fields inherently affected by imbalanced data is credit datasets in finance. In this study, to address this challenge, we employed one of the most recent methods developed for classifying imbalanced data, CorrOV-CSEn. In addition to the original CorrOV-CSEn approach, which uses AdaBoost as its base learning method, we also applied Multi-Layer Perceptron (MLP), random forest, gradient boosted trees, XGBoost, and CatBoost. Our dataset, sourced from the Iran capital market from 2015 to 2022, utilizes the more general and accurate term business failure instead of default. Model performance was evaluated using sensitivity, precision, and F1 score, while their overall performance was compared using the Friedman–Nemenyi test. The results indicate the high effectiveness of all models in identifying failing businesses (sensitivity), with CatBoost achieving a sensitivity of 0.909 on the test data. However, all models exhibited relatively low precision.