Year: 2025
Type: conference-paper
Abstract: ESG (Environmental, Social, and Governance) is an indicator of corporate sustainability and responsible performance in terms of environmental, social and governance, as well as an important framework for measuring corporate non-financial performance, which is important for balancing economic efficiency with global sustainable development. This study constructs the impact factor system of ESG index in the aspects of environment, society and governance, and then constructs six machine learning models to predict ESG index. The results show that LSTM model performs best, and MSE is 0.14-25.14 times better than other machine learning models BP, CNN, GRU, RNN and MLP. This study provides a scalable, intelligent solution for ESG assessment and reveals the potential value of deep learning in sustainable finance.
Author: Juantong Zhao
Institution: Nanjing Normal University
Language: English
Subfield: Strategy and Management
Domain: Social Sciences
Open Access status: gold
OpenAlex ID: W4412887602