Study on the Determinants of Corporate Green Innovation — A Study Based on XGBoost–SHAP Model

DOI

10.2991/978-2-38476-551-5_71How to use a DOI?

Keywords

green innovation; company development; machine learning; SHAP value; substantial development

Abstract

Green innovation is a key pathway for enterprises to achieve sustainable development, exploring its driving factors is essential to enhancing the level of corporate green innovation. This paper selects characteristic variables that may influence corporate green innovation from firms’ financial indicators, industry competition, and regional factors. It employs the nonlinear machine learning method XGBoost to fit the relationships between these variables and green innovation and uses SHAP values to measure the relative importance of each variable. The results show that firms’ R&D expenditure, institutional investor shareholding ratio, leverage ratio, firm size, firm age, industry competition, and financing constraints are the core drivers of corporate green innovation. Moreover, the driving factors differ across ownership types: for SOE companies and non-SOE companies, the importance of determinants varies. These findings provide valuable insights for policymakers aiming to promote green innovation across different ownership types.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Mohan Lin
PY  - 2026
DA  - 2026/03/26
TI  - Study on the Determinants of Corporate Green Innovation — A Study Based on XGBoost–SHAP Model
BT  - Proceeding of 2025 8th International Conference on Humanities Education and Social Sciences (ICHESS 2025)
PB  - Atlantis Press
SP  - 666
EP  - 672
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-551-5_71
DO  - 10.2991/978-2-38476-551-5_71
ID  - Lin2026
ER  -