Financial Risk Analysis for SMEs with Graph-based Supply Chain Mining

Yang, Shuo; Zhang, Zhiqiang; Zhou, Jun; Wang, Yang; Sun, Weiwei; Zhong, Xin; Fang, Yanming; Yu, Qian; Yuan, Qi

doi:10.24963/ijcai.2020/643

Cited by 56 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, Yang et al proposed a Spatial Temporal GNN (ST-GNN) to mine credible supply chain relationships, including risk analysis of small and medium-sized enterprises. 81 Wang et al proposed a Temporal-Aware GNN (TemGNN) to model the credit risk prediction on dynamic graphs. 76 Considering the time interval irregularity between dynamic snapshots, TemGNN adopts…”

Section: Deep-learning-based Approachesmentioning

confidence: 99%

Intelligent financial fraud detection practices in post-pandemic era

Zhu

Qin

et al. 2021

The Innovation

View full text Add to dashboard Cite

The great losses caused by financial fraud have attracted continuous attention from academia, industry, and regulatory agencies. More concerning, the ongoing coronavirus pandemic (COVID-19) unexpectedly shocks the global financial system and accelerates the use of digital financial services, which brings new challenges in effective financial fraud detection. This paper provides a comprehensive overview of intelligent financial fraud detection practices. We analyze the new features of fraud risk caused by the pandemic and review the development of data types used in fraud detection practices from quantitative tabular data to various unstructured data. The evolution of methods in financial fraud detection is summarized, and the emerging Graph Neural Network methods in the post-pandemic era are discussed in particular. Finally, some of the key challenges and potential directions are proposed to provide inspiring information on intelligent financial fraud detection in the future.

show abstract

Section: Deep-learning-based Approachesmentioning

confidence: 99%

Intelligent financial fraud detection practices in post-pandemic era

Zhu

Qin

et al. 2021

The Innovation

View full text Add to dashboard Cite

show abstract

“…Supply chain describes the supplier-customer relation between companies and it is proved to be useful in multiple financial tasks such as risk management (Yang et al, 2020) and performance prediction (Chen and Robert, 2021). We use the supply chain data from Factset 7 to build this graph.…”

Section: Supply Chainmentioning

confidence: 99%

Multivariate Realized Volatility Forecasting with Graph Neural Network

Chen¹,

Robert²

2021

Preprint

View full text Add to dashboard Cite

The existing publications demonstrate that the limit order book data is useful in predicting short-term volatility in stock markets. Since stocks are not independent, changes on one stock can also impact other related stocks. In this paper, we are interested in forecasting short-term realized volatility in a multivariate approach based on limit order book data and relational data. To achieve this goal, we introduce Graph Transformer Network for Volatility Forecasting. The model allows to combine limit order book features and an unlimited number of temporal and cross-sectional relations from different sources. Through experiments based on about 500 stocks from S&P 500 index, we find a better performance for our model than for other benchmarks.

show abstract

“…Y. Ren et al [12] utilized a bipartite graph to model the relationship between users and merchants and proposed an ensemble-based fraud detection method. S. Yang et al [13] applied a temporal graph to model financial relationships between enterprises to analyze financial risk.…”

Section: Related Workmentioning

confidence: 99%

DebtG: A Graph Model for Debt Relationship

Cui

2021

Information

View full text Add to dashboard Cite

Debt is common in daily transactions, but it may bring great harm to individuals, enterprises, and society and even lead to a debt crisis. This paper proposes a weighted directed multi-arc graph model DebtG of debts among a large number of entities, including individuals, enterprises, banks, and governments, etc. Both vertices and arcs of DebtG have attributes. In further, it defines three basic debt structures: debt path, debt tree, and debt circuit, and it presents algorithms to detect them and basic methods to solve debt clearing problems using these structures. Because the data collection and computation need a third-party platform, this paper also presents the profit analysis of the platform. It carries out a case analysis using the real-life data of enterprises in Huangdao Zone. Finally, it points out four key problems that should be addressed in the future.

show abstract

Financial Risk Analysis for SMEs with Graph-based Supply Chain Mining

Cited by 56 publications

References 7 publications

Intelligent financial fraud detection practices in post-pandemic era

Intelligent financial fraud detection practices in post-pandemic era

Multivariate Realized Volatility Forecasting with Graph Neural Network

DebtG: A Graph Model for Debt Relationship

Contact Info

Product

Resources

About