Graph neural network with self-attention and multi-task learning for credit default risk prediction
Publication Type
Conference Proceeding Article
Publication Date
11-2022
Abstract
We propose a graph neural network with self-attention and multi-task learning (SaM-GNN) to leverage the advantages of deep learning for credit default risk prediction. Our approach incorporates two parallel tasks based on shared intermediate vectors for input vector reconstruction and credit default risk prediction, respectively. To better leverage supervised data, we use self-attention layers for feature representation of categorical and numeric data; we further link raw data into a graph and use a graph convolution module to aggregate similar information and cope with missing values during constructing intermediate vectors. Our method does not heavily rely on feature engineering work and the experiments show our approach outperforms several types of baseline methods; the intermediate vector obtained by our approach also helps improve the performance of ensemble learning methods.
Keywords
Credit default risk prediction, Graph neural network, Self-attention, Multi-task learning
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces | Numerical Analysis and Scientific Computing
Research Areas
Data Science and Engineering
Publication
Web Information Systems Engineering, WISE 2022: 23rd International Conference, Biarritz, France, November 1-3: Proceedings
Volume
13742
First Page
616
Last Page
629
ISBN
9783031208911
Identifier
10.1007/978-3-031-20891-1_44
Publisher
Springer
City or Country
Cham
Citation
LI, Zihao; WANG, Xianzhi; YAO, Lina; CHEN, Yakun; XU, Guandong; and LIM, Ee-peng.
Graph neural network with self-attention and multi-task learning for credit default risk prediction. (2022). Web Information Systems Engineering, WISE 2022: 23rd International Conference, Biarritz, France, November 1-3: Proceedings. 13742, 616-629.
Available at: https://ink.library.smu.edu.sg/sis_research/7515
Additional URL
https://doi.org/10.1007/978-3-031-20891-1_44