Environmental risk assessment and green transformation path for sustainable development in the banking industry of Kyrgyz republic and China

As the global demand for sustainable development and green finance continues to increase, traditional banks have gradually exposed problems such as limited monitoring dimensions and delayed data response in environmental risk identification, green business promotion, and performance evaluation. To solve the above bottlenecks, this paper integrates artificial intelligence and Internet of Things technologies to build a green financial intelligent perception and control system. By applying an AI credit approval model, a real-time environmental data collection mechanism based on the Internet of Things, and a green performance intelligent tracking system, refined dynamic control of key indicators such as the proportion of green credit, environmental risk levels, and customer green satisfaction can be achieved. The experimental results show that the AI deep learning model performs best in green loan risk prediction, with an AUC (Area Under the Curve) value of 0.91, which is significantly higher than the 0.72 of the traditional credit scoring model and the 0.84 of the ESG enhanced model, indicating that the model has a stronger ability to distinguish between high-risk and low-risk loans. In the case of the simulated policy incentive bank, the initial green business accounts for 18.0%. Under the simulated policy incentive, the bank's green business accounts for 33.6%, an increase of 15.6%. This result shows that policy incentives have a significant promoting effect on underdeveloped banks.