基于机器学习的商业银行绿色信贷风险管理研究
Research on Green Credit Risk Management in Commercial Banks Based on Machine Learning
摘要: 本文通过构建基于大数据的综合评价体系，探讨提升绿色信贷风险评估效率和准确性的途径。选取了我国470家上市公司作为样本，运用SelectFromModel模型筛选关键指标，并结合SMOTE过采样算法处理样本不均衡问题。研究结果得出随机森林算法采用的机器学习模型更适用于评估绿色信贷风险。
Abstract: This paper explores approaches to enhance the efficiency and accuracy of green credit risk assessment by constructing a comprehensive evaluation system based on big data. A sample of 470 listed companies in China was selected, with the SelectFromModel used to screen key indicators, and the SMOTE oversampling algorithm employed to address sample imbalance issues. The research findings indicate that the machine learning model utilizing the Random Forest algorithm is more suitable for assessing green credit risk.
参考文献
|
[1]
|
李进. 基于随机森林算法的绿色信贷信用风险评估研究[J]. 金融理论与实践, 2015(11): 14-18.
|
|
[2]
|
Li, G. and Wu, Y. (2010) Empirical Research about Credit Risk on Neural Network Based Bp Algorithm. 2010 3rd International Conference on Information Management, Innovation Management and Industrial Engineering, Kunming, 26-28 November 2010, 461-463. [Google Scholar] [CrossRef]
|
|
[3]
|
王思宇, 陈建平. 基于LightGBM算法的信用风险评估模型研究[J]. 软件导刊, 2019, 18(10): 19-22.
|
|
[4]
|
García, V., Marqués, A.I. and Sánchez, J.S. (2014) An Insight into the Experimental Design for Credit Risk and Corporate Bankruptcy Prediction Systems. Journal of Intelligent Information Systems, 44, 159-189. [Google Scholar] [CrossRef]
|
|
[5]
|
张迪. 我国商业银行绿色信贷风险评估研究-基于模糊层次分析法和BP神经网络算法[J]. 山西农经, 2019(5): 147-148.
|
|
[6]
|
莫志宏, 唐迪, 葛林. 基于KMV模型的绿色信贷风险管理研究-来自风电和光伏产业的经验数据检验[J]. 管理现代化, 2015, 35(1): 97-99.
|
|
[7]
|
Farquad, M.A.H., Ravi, V., Sriramjee, and Praveen, G. (2011) Credit Scoring Using PCA-SVM Hybrid Model. In: Das, V.V., Stephen, J. and Chaba, Y., Eds., Computer Networks and Information Technologies, Springer, 249-253. [Google Scholar] [CrossRef]
|