Abstract
The traditional financial models used in bond default mainly focus on the analysis and prediction of bonds issued by listed companies, and they lack early warning abilities for a large number of bonds of nonlisted companies. At the same time, there is a great deal of relational data and category data in bond data. It is of great significance for bond default prediction to use these data reasonably, which may bring considerable revenue to companies in the near future. Therefore, this paper uses multisource information from bonds and issuers as well as macroeconomic data to predict bond defaults based on a knowledge graph and deep learning technology. On the basis of constructing a bond knowledge graph, knowledge representation learning technology is used to vectorize the knowledge in the graph, and the extracted vectors are inputted into the deep learning model as features to forecast bond default. The applied model is the deep factorization machine model, and good prediction results are obtained.
Highlights
With the recent epidemic of credit risk in the bond market, bond defaults have occurred frequently in China, especially in 2018
Based on the Deep Factorization Machines (DeepFM) model, this paper introduces the knowledge graph as feature embedding of the model and proposes an optimized DeepFM model that integrates the knowledge graph information
According to the characteristics of publicly available bond data, this paper proposes a deep learning model that integrates the semantic information of a knowledge graph and applies it to bond default prediction
Summary
1,2 , of Computer Science and Engineering, Huizhou University, Huizhou 516007, China of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China. This work was supported in the part by the Foundation of Guangdong Educational Committee under Grant 2018KTSCX218, and in the part by the Professorial and Doctoral Scientific Research Foundation of Huizhou University under Grant 2018JB020
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
