Aggregating multiple classification results using Choquet integral for financial distress early warning |
| |
Authors: | Yu Cao |
| |
Affiliation: | Business School, Central South University, 932, Southern Lushan Road, Changsha 410083, China |
| |
Abstract: | Financial distress prediction methods based on combination classifier become a rising trend in this field. This paper applies Choquet integral to ensemble single classifiers and proposes a Choquet integral-based combination classifier for financial distress early warning. Also, as the conditions between training and pattern recognition cannot be completely consistent, so this paper proposes an adaptive fuzzy measure by using the dynamic information in the single classifier pattern recognition results which is more reasonable than the static prior fuzzy density. Finally, a comparative analysis based on Chinese listed companies’ real data is conducted to verify prediction accuracy and stability of the combination classifier. The experiment results indicate that financial distress prediction using Choquet integral-based combination classifier has higher average accuracy and stability than single classifiers. |
| |
Keywords: | Choquet integral Fuzzy measure Financial distress Early warning Empirical risk |
本文献已被 ScienceDirect 等数据库收录! |
|