Progress in Applying Artificial Intelligence to ESG Data Acquisition and Financial Analysis

With the growing demand for sustainable finance and investment decision-making, the role of artificial intelligence (AI) in environmental, social, and governance (ESG) data collection and analysis has attracted increasing scholarly attention. Nevertheless, challenges such as fragmented data sources and inconsistent standards continue to limit its application. Against this backdrop, this study reviews prior research to outline recent progress in ESG data collection, risk identification, and financial analysis, while also evaluating AIs role in improving data reliability, guiding investment strategies, and strengthening risk control. The results reveal that techniques such as natural language processing (NLP), machine learning, and generative AI can strengthen ESG data collection and analytical capacity, with practical applications in risk identification, portfolio optimization, and asset pricing. Yet, practical applications are constrained by issues such as inconsistent data standards, algorithmic bias, and the lack of model interpretability. Future research should prioritize the establishment of unified data standards, the enhancement of algorithmic fairness and interpretability, and the advancement of multimodal data integration and cross-regional comparisons to develop a more intelligent and reliable ESG analytical framework.