Affiliations: [a] Shandong Transport Vocational College, Weifang, Shandong, China
| [b] School of Economics and Finance, Massey University, Palmerston North, New Zealand
Correspondence:
[*]
Corresponding author. Ke Wang, Shandong Transport Vocational College, Weifang 261206, Shandong, China. E-mail: [email protected].
Abstract: With the rapid economic development and increasingly serious environmental problems, many regions have launched green credit policies. Green credit can reduce the loan interest rate of the environmental protection industry and lower the financing threshold. Traditional risk prediction methods cannot comprehensively evaluate the green credit risk of the enterprise based on the degree of green environmental protection and the industry environment in which the enterprise is located, resulting in the inconsistency between the credit financial risk prediction and the actual results, which increases the bank credit risk. In order to strengthen the management level of green credit and reduce the probability of non-performing loans, a scientific risk assessment method was constructed by using a combination of automatic encoding network and bidirectional long short-term memory neural network model to predict the financial risks of green credit, driven by multi-modal data. Through the study of multimodal data, this paper took green credit financial risk as the research object, aggregated the information of various enterprises to improve the bank’s capital utilization rate, and also promoted enterprises to take the initiative to transform into the direction of green environmental protection. Finally, the experiment proved that multimodal data fusion model was more superior than random forest in risk prediction, reducing the bank’s non-performing loan rate by 3.1% and improving the bank’s risk control level.
Keywords: Financial risk, green credit, risk prediction, multimodal data
