Prediction of Manufacturing Corporates Bankruptcy Using Ensemble Learning Method
The bankruptcy of manufacturing corporates is an important factor affecting economic stability.Corporate bankruptcy has become a hot research topic mainly through financial data analysis and prediction.With the development of data science and artificial intelligence, machine learning technology helps researchers improve the accuracy and robustness of classification models.In this study, we proposed a bankruptcy classification model combining Synthetic Minority Oversampling Technique (SMOTE) imbalanced data learning algorithm, multi-interval discretization filter and ensemble learning method.To verify the proposed model, we conducted comparative experiments with ten other baseline classifiers, and proved that SMOTE imbalanced learning algorithm and features processing with multi-interval discretization were effective.The final results show that our proposed model has achieved better performance and robustness than other baseline classifiers in terms of classification accuracy, F-measure and AuROC Area under Curve (AUC).
Data Mining Corporate Bankruptcy Prediction Ensemble Learning
Xiaoxia Wu Dongqi Yang Wenyu Zhang Shuai Zhang
Department of Financial Accounting Zhejiang Institute of Economics and Trade Hangzhou,China School of Information Zhejiang University of Finance and Economics Hangzhou,China
国际会议
郑州
英文
261-267
2018-09-21（万方平台首次上网日期，不代表论文的发表时间）