Graph neural network with self-attention and multi-task learning for credit default risk prediction

• Main Authors: LI, Zihao, WANG, Xianzhi, YAO, Lina, CHEN, Yakun, XU, Guandong, LIM, Ee-peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Credit default risk prediction; Graph neural network; Self-attention; Multi-task learning; Databases and Information Systems; Graphics and Human Computer Interfaces; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/7515; https://doi.org/10.1007/978-3-031-20891-1_44
• Institution: Singapore Management University

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.