Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach

As Chinese firms play pivotal roles in global supply chains, multinational corporations face increasing pressure to ensure ESG accountability across their sourcing networks. Current ESG rating systems lack transparency in incorporating China’s unique industrial, economic, and cultural factors, creat...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyojin Kim, Myounggu Lee
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Systems
Subjects:
Online Access:https://www.mdpi.com/2079-8954/13/7/578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850071172466606080
author Hyojin Kim
Myounggu Lee
author_facet Hyojin Kim
Myounggu Lee
author_sort Hyojin Kim
collection DOAJ
description As Chinese firms play pivotal roles in global supply chains, multinational corporations face increasing pressure to ensure ESG accountability across their sourcing networks. Current ESG rating systems lack transparency in incorporating China’s unique industrial, economic, and cultural factors, creating reliability concerns for stakeholders managing supply chain sustainability risks. This study develops an explainable artificial intelligence framework using SHAP and permutation feature importance (PFI) methods to predict the ESG performance of Chinese firms. We analyze comprehensive ESG data of 1608 Chinese listed companies over 13 years (2009–2021), integrating financial and non-financial determinants traditionally examined in isolation. Empirical findings demonstrate that random forest algorithms significantly outperform multivariate linear regression in capturing nonlinear ESG relationships. Key non-financial determinants include patent portfolios, CSR training initiatives, pollutant emissions, and charitable donations, while financial factors such as current assets and gearing ratios prove influential. Sectoral analysis reveals that manufacturing firms are evaluated through pollutant emissions and technical capabilities, whereas non-manufacturing firms are assessed on business taxes and intangible assets. These insights provide essential tools for multinational corporations to anticipate supply chain sustainability conditions.
format Article
id doaj-art-48d4f62f7ece4c36bcfb1aa5f70c308c
institution DOAJ
issn 2079-8954
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Systems
spelling doaj-art-48d4f62f7ece4c36bcfb1aa5f70c308c2025-08-20T02:47:22ZengMDPI AGSystems2079-89542025-07-0113757810.3390/systems13070578Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning ApproachHyojin Kim0Myounggu Lee1School of Business, Konkuk University, Seoul 05029, Republic of KoreaSchool of Business, Konkuk University, Seoul 05029, Republic of KoreaAs Chinese firms play pivotal roles in global supply chains, multinational corporations face increasing pressure to ensure ESG accountability across their sourcing networks. Current ESG rating systems lack transparency in incorporating China’s unique industrial, economic, and cultural factors, creating reliability concerns for stakeholders managing supply chain sustainability risks. This study develops an explainable artificial intelligence framework using SHAP and permutation feature importance (PFI) methods to predict the ESG performance of Chinese firms. We analyze comprehensive ESG data of 1608 Chinese listed companies over 13 years (2009–2021), integrating financial and non-financial determinants traditionally examined in isolation. Empirical findings demonstrate that random forest algorithms significantly outperform multivariate linear regression in capturing nonlinear ESG relationships. Key non-financial determinants include patent portfolios, CSR training initiatives, pollutant emissions, and charitable donations, while financial factors such as current assets and gearing ratios prove influential. Sectoral analysis reveals that manufacturing firms are evaluated through pollutant emissions and technical capabilities, whereas non-manufacturing firms are assessed on business taxes and intangible assets. These insights provide essential tools for multinational corporations to anticipate supply chain sustainability conditions.https://www.mdpi.com/2079-8954/13/7/578ESGcorporate social responsibilityexplainable machine learningSHapley Additive exPlanationssupply chain sustainability
spellingShingle Hyojin Kim
Myounggu Lee
Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
Systems
ESG
corporate social responsibility
explainable machine learning
SHapley Additive exPlanations
supply chain sustainability
title Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
title_full Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
title_fullStr Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
title_full_unstemmed Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
title_short Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
title_sort unraveling the drivers of esg performance in chinese firms an explainable machine learning approach
topic ESG
corporate social responsibility
explainable machine learning
SHapley Additive exPlanations
supply chain sustainability
url https://www.mdpi.com/2079-8954/13/7/578
work_keys_str_mv AT hyojinkim unravelingthedriversofesgperformanceinchinesefirmsanexplainablemachinelearningapproach
AT myounggulee unravelingthedriversofesgperformanceinchinesefirmsanexplainablemachinelearningapproach