基于深度神经网络的银行信贷风险监测模型研究及实现

发布时间：2018-03-13 13:01

本文选题：商业银行　切入点：信贷风险　出处：《郑州大学》2016年硕士论文　论文类型：学位论文

【摘要】：信贷风险的发生对于一国的金融和经济发展将会产生严重的负面影响。我国信贷风险管理方法和技术发展缓慢,大多国有商业银行依旧只能简单的使用国外管控模型和基本的案例证实,并不完全具备预测和掌控信贷风险的能力。因此针对我国商业银行信贷风险的特点,急需建立一种有效的风险监测模型。人工智能技术的兴起、完善和大规模银行数据的产生,为构建更有效的信贷风险监测模型提供了新的方向。深度神经网络应用广泛,有着优异的特征学习能力和大规模数据拟合能力,是最有效的人工智能技术之一。通过参考国外商业银行信贷风险管理经验,基于我国银行真实的管理模式和经营环境,提出了一种基于深度神经网络的银行信贷风险监测模型,优化训练方法,经实际测试效果显著,主要内容如下:1.通过深入分析影响信贷风险的因素,遵循指标构建的原则,针对农发行某分行贷款企业的特点,完善、构建了相对全面的信贷风险监测指标体系。该指标体系既包含了重要的财务收益指标,也包含现金流量、企业成长性、规模等相关指标,能够全面、综合的反映贷款企业的风险状况。通过统计学的方法,对原始指标数据筛选出区分能力强的指标,进行因子分析。2.针对传统方法的不足,使用深度神经网络进行信贷风险评估,并设计了适用于实际风险评估的模型结构和参数。本文将最新的人工智能技术,深度神经网络方法,应用到信贷风险监测领域,拓宽了银行风险监测和管理的方法和思路。3.本文以农发行某分行的信贷风险状况作为实例研究,并结合我国银行的共性问题,设计了深度神经网络风险监测模型,既使用了统计学的方法,如显著性检验、因子分析等,也使用了最新的深度神经网络技术。通过实际数据验证,比传统k近邻方法、逻辑回归方法、BP神经网络方法具有更高的风险识别准确率,能够应用在实际的风险监测工作,指导业务实践。
[Abstract]:The occurrence of credit risk will have a serious negative impact on the financial and economic development of a country. Most state-owned commercial banks can only simply use foreign control models and basic cases to prove that they do not have the ability to predict and control credit risk. Therefore, in view of the characteristics of credit risk of commercial banks in China, It is urgent to establish an effective risk monitoring model. The rise of artificial intelligence technology, perfection and the production of large-scale bank data provide a new direction for the construction of more effective credit risk monitoring model. Depth neural network is widely used. It is one of the most effective artificial intelligence technology, which has excellent characteristic learning ability and large scale data fitting ability. By referring to the credit risk management experience of foreign commercial banks, based on the real management model and operating environment of Chinese banks, In this paper, a bank credit risk monitoring model based on deep neural network is put forward, and the training method is optimized. The practical test results are remarkable. The main contents are as follows: 1. Through in-depth analysis of the factors affecting credit risk, we follow the principle of index construction. According to the characteristics of a branch loan enterprise of Agricultural Development Bank, a relatively comprehensive credit risk monitoring index system is constructed. The index system includes not only important financial income index, but also cash flow, enterprise growth, and so on. Scale and other related indicators can comprehensively and synthetically reflect the risk situation of loan enterprises. Through the statistical method, the original index data can be screened out with strong distinguishing ability, and factor analysis .2. in view of the shortcomings of traditional methods, In this paper, the new artificial intelligence technology, the depth neural network method, is applied to the credit risk monitoring field, and the model structure and parameters suitable for the actual risk assessment are designed by using the depth neural network. 3. Taking the credit risk situation of a branch of Agricultural Development Bank as an example, and combining the common problems of Chinese banks, a deep neural network risk monitoring model is designed. It not only uses statistical methods, such as significance test, factor analysis and so on, but also uses the latest depth neural network technology. The logical regression method and BP neural network method have higher risk identification accuracy and can be applied to practical risk monitoring and guiding business practice.
【学位授予单位】：郑州大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP183;F832.4

【相似文献】