Affiliations: [a] School of Engineering and Management, Nanjing University, Nanjing, China
| [b]
Postdoctoral Research Station, Shanghai Stock Exchange, Shanghai, China
Correspondence:
[*]
Corresponding author. Binqing Xiao, School of Engineering and Management, Nanjing University, Nanjing 210093, China. E-mail: [email protected].
Abstract: This study identifies credit risk sources, credit scoring index classification modes and modelling methods, and constructs a credit scoring system for small and micro businesses (SMBs) with soft information. Through the analysis and comparison of neural network models, this study demonstrates the superiority of the back-propagation neural network (BPNN) models for loan classification prediction. There are three contributions and innovations as follows. (1) Based on the actual demands and default characteristics of SMBs, this study adds the behavioural variables of loan managers to strengthen the role of soft information in credit scoring model. (2) It develops a hybrid analysis and comparison framework based on the BPNN model. It identifies that the BPNN model is more suitable for approving SMB loans, as it can precisely identify the second type of error. (3) Using the precious ledger data of SMB loans from a rural commercial bank in Jiangsu province, China, this study compares the prediction accuracy of the credit scoring model based on BPNN using two-level and five-level loan classifications. Further, it illustrates the applicability of the BPNN model. By connecting the practical operations of credit scoring and quantitative models, this paper supports commercial bank examination and approval work of SMB loans.
Keywords: Credit scoring, small and micro businesses, soft information, back-propagation neural network, comparative analysis
