Machine Learning for Predicting Corporate Violations: How Do CEO Characteristics Matter?

Based on upper echelon theory, we employ machine learning to explore how CEO characteristics influence corporate violations using a large-scale dataset of listed firms in China for the period 2010–2020. Comparing ten machine learning methods, we find that eXtreme Gradient Boosting (XGBoost) outperfo...

Full description

Saved in:
Bibliographic Details
Published in:Journal of business ethics 2024-11, Vol.195 (1), p.151-166
Main Authors: Sun, Ruijie, Liu, Feng, Li, Yinan, Wang, Rongping, Luo, Jing
Format: Article
Language:English
Subjects:
Business and Management
Business Ethics
Corporate governance
Education
Ethics
Financial market
Machine learning
Management
Marketing
Original Paper
Philosophy
Quality of Life Research
R&D
Research & development
Violations
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Based on upper echelon theory, we employ machine learning to explore how CEO characteristics influence corporate violations using a large-scale dataset of listed firms in China for the period 2010–2020. Comparing ten machine learning methods, we find that eXtreme Gradient Boosting (XGBoost) outperforms the other models in predicting corporate violations. An interpretable model combining XGBoost and SHapley Additive exPlanations (SHAP) indicates that CEO characteristics play a central role in predicting corporate violations. Tenure has the strongest predictive power and is negatively associated with corporate violations, followed by marketing experience, education, duality (i.e., simultaneously holding the position of chairperson), and research and development experience. In contrast, shareholdings, age, and pay are positively related to corporate violations. We also analyze violation severity and violation type, confirming the role of tenure in predicting more severe and intentional violations. Overall, our findings contribute to preventing corporate violations, improving corporate governance, and maintaining order in the financial market.
ISSN:0167-4544
1573-0697
DOI:10.1007/s10551-024-05685-0