An evidence-based credit evaluation ensemble framework for online retail SMEs

摘要

The lack of standardized financial statements makes it difficult to determine the credit ratings of small and medium-sized enterprises (SMEs). Focusing on this problem, we construct an ensemble framework based on evidence theory. First, we change the sale amount to cash flow lift through a difference table. Then, we analyse consumer comments using the high-frequency lexical sentiment degree. Finally, we combine the two results with an orthogonal sum according to the principle of evidence theory. Based on this framework, we take an online candy company, “Da Bai Tu” in Tmall, as a case to illustrate the application of this framework. Based on experiments with 50 candy SMEs, the degree scores of the framework and Tmall stores are consistent in a one-way ANOVA. The framework effectively combines objective sales records and subjective comments; thus, it can solve the difficulty in credit evaluation for SMEs.