Abstract
AbstractThis paper aims to enhance the resilience of financial enterprises against environmental risks by leveraging financial data analysis tools. The approach involves designing environmental risk assessment indicators and rating criteria. The study utilizes a convolutional neural network model extended by a multi-scale feature fusion module to analyze environmental risk information in the industry. The proposed model achieves impressive results with accuracy (Acc), precision (P), recall (R), and F1 scores reaching 99.09, 96.31, 95.32, and 95.64, respectively. These metrics outperform those of comparison models. The success of this model is anticipated to pave the way for the transformation of green finance through automated industry-level environmental risk assessment. Furthermore, the method’s adaptability extends beyond environmental risks, offering a scalable solution for identifying and assessing environmental risks in various contexts.
Publisher
Springer Science and Business Media LLC
Reference30 articles.
1. Chen, J., Wang, Q., Peng, W., Xu, H., Li, X., & Xu, W. (2022). Disparity-based multi-scale fusion network for transportation detection. IEEE Transactions on Intelligent Transportation Systems, 23(10), 18855–18863.
2. Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.
3. Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251–1258).
4. Ding, S. F., Zhu, Z. B., & Zhang, X. K. (2017). An overview on semi-supervised support vector machine. Neural Computing and Applications, 28, 969–978.
5. Dogan, A., & Birant, D. (2021). Machine learning and data mining in manufacturing. Expert Systems with Applications, 166, 114060.