Due to the powerful learning ability on high-rank and non-linear features, deep neural networks (DNNs) are being applied to data mining and machine learning in various fields, and exhibit higher discrimination performance than conventional methods. However, the applications based on DNNs are rare in enterprise credit rating tasks because most of DNNs employ the "end-to-end" learning paradigm, which outputs the high-rank representations of objects and predictive results without any explanations. Thus, users in the financial industry cannot understand how these high-rank representations are generated, what do they mean and what relations exist with the raw inputs. Then users cannot determine whether the predictions provided by DNNs are reliable, and not trust the predictions providing by such "black box" models. Therefore, in this paper, we propose a novel network to explicitly model the enterprise credit rating problem using DNNs and attention mechanisms. The proposed model realizes explainable enterprise credit ratings. Experimental results obtained on real-world enterprise datasets verify that the proposed approach achieves higher performance than conventional methods, and provides insights into individual rating results and the reliability of model training.
翻译:由于高层次和非线性特征的强大学习能力,深神经网络(DNNs)被应用于数据挖掘和各个领域的机器学习,并表现出比常规方法更高的歧视性性能。然而,基于DNS的应用在企业信用评级任务中是罕见的,因为大多数DNS采用“端到端”学习模式,在不作任何解释的情况下产生高层次物体和预测结果的高层次表现。因此,金融业的用户无法理解这些高层次表现是如何产生的,它们意味着什么,与原始投入的关系是什么。然后,用户无法确定DNS提供的预测是否可靠,而不相信这种“黑盒”模式提供的预测。因此,在本文件中,我们提议建立一个新的网络,用DNNs和关注机制明确模拟企业信用评级问题。拟议的模型实现了可解释的企业信用评级。在现实世界企业数据集上取得的实验结果证实,拟议的方法取得了比常规方法更高的业绩,并且提供了个人评级结果和示范培训可靠性的洞察力。