Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2025

Abstract

Potential risk signals reflected in supply chain and equity connections between enterprises and social connections between investors are becoming crucial to identifying enterprise risks in addition to basic financial indicators. Traditional risk management systems face challenges in adapting to these complexities, highlighting the need for a proactive paradigm shift in risk management. Leveraging graph models such as social networks and knowledge graphs offers a promising approach to identifying and managing potential associated risks effectively. To bridge existing research gaps, a novel risk identification framework driven by social-knowledge graphs has been proposed, integrating graph deep learning and reinforcement learning techniques guided by design science. This hybrid model enhances risk warning levels by considering “socio knowledge associations”, improving interpretability, and fostering collaborative learning mechanisms for more effective risk recognition in dynamic environments.

Keywords

Enterprise Risk Identification, Socio-Knowledge Association, Social-Knowledge Graph, Graph Deep Learning, Reinforcement Learning, Design Science Research

Discipline

Databases and Information Systems | Finance and Financial Management

Research Areas

Data Science and Engineering

Publication

CSWIM 2025: 18th China Summer Workshop on Information Management, June 28-29, Xi'an: Proceedings

First Page

457

Last Page

462

Publisher

China Summer Workshop on Information Management

City or Country

China

Download

Share

COinS