Journal of
Accounting and Taxation

  • Abbreviation: J. Account. Taxation
  • Language: English
  • ISSN: 2141-6664
  • DOI: 10.5897/JAT
  • Start Year: 2009
  • Published Articles: 206

Full Length Research Paper

Design and development of credit rating model for public sector banks in India: Special reference to small and medium enterprises

Srinvas Gumparthi1*, Swetha Khatri1 and V. Manickavasagam2
1 SSN School of Management and Computer Applications, Chennai, India. 2Department of Corporate Secretaryship Alagappa University, Karaikudi, India.
Email: [email protected];[email protected].

  •  Accepted: 24 June 2011
  •  Published: 30 September 2011


This research focuses on the design and development of the credit rating model for public sector banks in India. The need to enhance the existing model and to realize the impact of BASEL II Norms was the reason for the development of the models. Also, the absence of appropriate weights in the current system triggers the need for the development of the same model. Different models were constructed using weighted average method and discriminant analysis. Under the weighted average model, various risks and their sub-parameters were identified. The parameters were classified under four heads namely: industry, business, financial and management risk. The weights developed in this study were based on a conceptual understanding and the importance attached by people that are proficient in this area. A questionnaire was developed and a judgmental survey was conducted among 15 banks with 30 credit rating managers extending the loans of small and medium enterprises (SME). A total of 35 cases were taken for the validation of the model. The new model was able to classify 32 records correctly out of the 35 cases. Further, discriminant analysis was used to classify objects/records into two or more groups based on the knowledge of some variables related to them. Under the discriminant model, the sample size taken was 100 clients of the corporate banking branch. Census was used as the sampling technique, in which 69 records were taken for the development of the model and 31 for validation. However, discriminant functions were constructed, and it was observed that the discriminant and classification scores aided in the classification of the clients. The discriminant model was able to classify 27 records correctly out of 31 cases. Thus, it was concluded that the weighted average model can be used for predicting the credit worthiness of the clients because it has higher predictive power.


Key words: Small and medium enterprise (SME), discriminant, commercial banks, credit risk, credit risk model.