Multiview Graph Learning for Small- and Medium-Sized Enterprises’ Credit Risk Assessment in Supply Chain Finance

In recent years, supply chain finance (SCF) is exploited to solve the financing difficulties of small- and medium-sized enterprises (SMEs). SME credit risk assessment a critical part in SCF system. The diffusion may cause serious consequences, leading whole system unstable insecure. Compared with traditional models, relationship, condition SME, core should all be considered rate SCF. Traditional methods mix indicators from different index systems. They cannot give quantitative result on how these systems work. Furthermore, models are heavily dependent number annotated data. However, it implausible accumulate enough risky SMEs advance. this paper, we propose an adaptive heterogenous multiview graph learning method tackle small sample size problem for SMEs’ forecasting. Three graphs constructed by using operation, financial indicator, nonfinancial indicator individually. All integrated manner, providing explanation three parts cooperate. experimental analysis shows that proposed has good performance determining whether or nonrisky From perspective SCF, ability still main factor determine SME.