JIANGHAN ACADEMIC ›› 2025, Vol. 44 ›› Issue (1): 83-94.doi: 10.16388/j.cnki.cn42-1843/c.2025.01.008
Previous Articles
PENG Ying1,2,ZHANG Ziye1
Received:
Online:
Published:
Abstract: Green technological innovation is key to the green and low-carbon development,which takes into account both economic and environmental benefits. Heavy polluting A-share listed enterprises from 2011 to 2020 are sampled;the capacity of different multi-dimensional green technological innovation motivations in predicting green technology innovation behavior is explored by using the parametric method, non-parametric method,and ensemble learning method in machine learning. The purpose is to identify the main motivation affecting enterprises to carry out green technology innovation and identify features of the most predictive quality. The results show that compared with the digital development motivation and the internal governance motivation,the external supervision motivation is the main driver for the green technology innovation behavior of enterprises;the ability of ensemble learning method to predict green technology innovation behavior is better than that of parametric and non-parametric research methods,and the support vector machine has the strongest interpretation ability and the highest prediction accuracy;and among the multi-dimensional motivation features,digital finance,corporate social responsibility,and government environmental protection subsidies have the best predictive effect on green technology innovation behavior. Applying the machine learning method can effectively identify the key factors of green technology innovation in enterprises,and is enlightening for the sustainable development of enterprises and the construction of ecological civilization.
Key words: green technological innovation, machine learning, ensemble learning, construction of ecological civilization
CLC Number:
X322
F273.1
PENG Ying,ZHANG Ziye. Multidimensional Drivers and Key Factors of Green Technological Innovation of Enterprise:Evidence Based on Machine Learning[J]. JIANGHAN ACADEMIC, 2025, 44(1): 83-94.
0 / / Recommend
Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks
URL: https://qks.jhun.edu.cn/jhxs/EN/10.16388/j.cnki.cn42-1843/c.2025.01.008
https://qks.jhun.edu.cn/jhxs/EN/Y2025/V44/I1/83