Research Article
Research on the Knowledge Map in the Prediction of Bond Default
@INPROCEEDINGS{10.4108/eai.17-6-2022.2322865, author={Hui Hu and Anxu Bu and Le Yang and Chi Ma}, title={Research on the Knowledge Map in the Prediction of Bond Default}, proceedings={Proceedings of the International Conference on Information Economy, Data Modeling and Cloud Computing, ICIDC 2022, 17-19 June 2022, Qingdao, China}, publisher={EAI}, proceedings_a={ICIDC}, year={2022}, month={10}, keywords={component; default prediction; deepfm; knowledge map; knowledge representation learning}, doi={10.4108/eai.17-6-2022.2322865} }- Hui Hu
Anxu Bu
Le Yang
Chi Ma
Year: 2022
Research on the Knowledge Map in the Prediction of Bond Default
ICIDC
EAI
DOI: 10.4108/eai.17-6-2022.2322865
Abstract
When solving the problem of bond default, because there is a lot of relational and categorical data in the bond data, reasonable use of these data to predict bond defaults is of great significance. Based on the construction of bonding knowledge map, in this paper, knowledge representation learning is used to vectorize the knowledge of picture, and the extracted vector is input into the deepfm model as a feature to predict whether the bond will default. Compared with the general traditional bond default prediction method, in this paper, knowledge map is introduced as the feature embedding of bond default prediction model. The experimental results show that it has higher prediction accuracy.
Copyright © 2022–2024 EAI