Executive Party Characteristics and Financial Irregularities-Predictive Identification Based on Random Forest Algorithm DOI Creative Commons
Yi Zhang

International Journal of Global Economics and Management, Год журнала: 2024, Номер 5(1), С. 215 - 227

Опубликована: Ноя. 11, 2024

As capital markets evolve, corporate financial misconduct garners more scrutiny. This study, using data from China's A-share companies (2006-2023), develops a model to predict irregularities with the random forest algorithm and SHAP value analysis. It analyzes influence of governance executive party traits on non-compliance their predictive roles. Findings indicate that characteristics significantly impact predictions, while have lower influence. The model's AUC improves inclusion characteristics. analysis highlights feature importance direction. results offer practical insights for regulators, companies, investors, aiding regulatory efficiency, optimization, investment decisions, guide strategies market health.

Язык: Английский

The role of interlocking directorates and managerial characteristics on corporate green innovation DOI
Xiaoyue Zhang, Weizheng Sun

Finance research letters, Год журнала: 2025, Номер 74, С. 106818 - 106818

Опубликована: Янв. 17, 2025

Язык: Английский

Процитировано

0
Does third-party monitoring reduce environmental violations in mining firms? DOI

Renjie Zhou,

Yongheng Luo, Zhengye Gao

и другие.

Resources Policy, Год журнала: 2025, Номер 103, С. 105565 - 105565

Опубликована: Март 20, 2025

Язык: Английский

Процитировано

0
The role of media exposure on board capital and carbon emission disclosure DOI Creative Commons

Mohammad Syafik,

Doddy Setiawan, Sri Hartoko

и другие.

Discover Sustainability, Год журнала: 2025, Номер 6(1)

Опубликована: Апрель 11, 2025

Язык: Английский

Процитировано

0
Executive Party Characteristics and Financial Irregularities-Predictive Identification Based on Random Forest Algorithm DOI Creative Commons
Yi Zhang

International Journal of Global Economics and Management, Год журнала: 2024, Номер 5(1), С. 215 - 227

Опубликована: Ноя. 11, 2024

As capital markets evolve, corporate financial misconduct garners more scrutiny. This study, using data from China's A-share companies (2006-2023), develops a model to predict irregularities with the random forest algorithm and SHAP value analysis. It analyzes influence of governance executive party traits on non-compliance their predictive roles. Findings indicate that characteristics significantly impact predictions, while have lower influence. The model's AUC improves inclusion characteristics. analysis highlights feature importance direction. results offer practical insights for regulators, companies, investors, aiding regulatory efficiency, optimization, investment decisions, guide strategies market health.

Язык: Английский

Процитировано

0