A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance

Supply Chain Finance (SCF) has gradually taken on digital characteristics with the rapid development of electronic information technology. Business audit become more abundant and complex, which increased efficiency potential risk commercial banks, credit being biggest they face. Therefore, assessment based application SCF is great importance to banks’ financial decisions. This paper uses a hybrid Extreme Gradient Boosting Multi-Layer Perceptron (XGBoost-MLP) model assess Digital (DSCF). In this paper, 1357 observations from 85 Chinese-listed SMEs over period 2016–2019 are selected as empirical sample, important features in DSCF automatically through feature selection XGBoost first stage, then followed by MLP second stage. Based results, we find that XGBoost-MLP good performance assessment, where for model. From perspective DSCF, results show inclusion improves accuracy SCF.