An Enhanced Cascading Model for E-Commerce Consumer Credit Default Prediction

As an important global policy guide to promote economic transformation and upgrading, the upsurge of E-Commerce has been continuously upgraded with continuous breakthroughs in information technology. In recent years, China’s e-commerce consumer credit developed well, but due its short time production insufficient experience for reference, risk, fraud regulatory risk continue emerge. Aiming at problem Consumer Credit default analysis, this paper proposes a Fusion Enhanced Cascade Model (FECM). This model learns feature data by fusing multi-granularity modules, incorporates random forest GBDT trade-off variance bias methods. The compares FECM gcForest on multiple sets, prove applicability field E-commerce prediction. research results are helpful control financial development, construct relatively stable space promoting construction development E-Commerce.