The work reported in this paper aims to present possibility distribution model of soft data used for corporate client credit risk assessment in commercial banking by applying Type 2 fuzzy membership functions (distributions) for the purpose of developing a new expert decision-making fuzzy model for evaluating credit risk of corporate clients in a bank. The paper is an extension of previous research conducted on the same subject which was based on Type 1 fuzzy distributions. Our aim in this paper is to address inherent limitations of Type 1 fuzzy distributions so that broader range of banking data uncertainties can be handled and combined with the corresponding hard data, which all affect banking credit decision making process. Banking experts were interviewed about the types of soft variables used for credit risk assessment of corporate clients, as well as for providing the inputs for generating Type 2 fuzzy logic membership functions of these soft variables. Similar to our analysis with Type 1 fuzzy distributions, all identified soft variables can be grouped into a number of segments, which may depend on the specific bank case. In this paper we looked into the following segments: (i) stability, (ii) capability and (iii) readiness/willingness of the bank client to repay a loan. The results of this work represent a new approach for soft data modeling and usage with an aim of being incorporated into a new and superior soft-hard data fusion model for client credit risk assessment.

This study introduces Uncertainty Balance Principle (UBP) as a new concept/method for incorporating additional soft data into probabilistic credit risk assessment models. It shows that soft banking data, used for credit risk assessment, can be expressed and decomposed using UBP and thus enabling more uncertainty to be handled with a precise mathematical methodology. The results show that this approach has relevance to credit risk assessment models in the sense that it proved its usefulness for the purpose of soft-hard data fusion, it modified Probability of Default with soft data modeled using possibilistic (fuzzy) distributions and fused with hard probabilistic data via UBP and it obtained better classification prediction results on the overall sample. This was demonstrated on a simple example of one soft variable, two experts and a small sample and thus this is an approach/method that requires further research, enhancements and rigorous statistical testing for the application to a complete scoring and/or rating system

No abstract

No abstract

The work reported in this paper aims to present possibility distribution model of soft data used for corporate client credit risk assessment in commercial banking by applying Type 2 fuzzy membership functions (distributions) for the purpose of developing a new expert decision-making fuzzy model for evaluating credit risk of corporate clients in a bank. The paper is an extension of previous research conducted on the same subject which was based on Type 1 fuzzy distributions. Our aim in this paper is to address inherent limitations of Type 1 fuzzy distributions so that broader range of banking data uncertainties can be handled and combined with the corresponding hard data, which all affect banking credit decision making process. Banking experts were interviewed about the types of soft variables used for credit risk assessment of corporate clients, as well as for providing the inputs for generating Type 2 fuzzy logic membership functions of these soft variables. Similar to our analysis with Type 1 fuzzy distributions, all identified soft variables can be grouped into a number of segments, which may depend on the specific bank case. In this paper we looked into the following segments: (i) stability, (ii) capability and (iii) readiness/willingness of the bank client to repay a loan. The results of this work represent a new approach for soft data modeling and usage with an aim of being incorporated into a new and superior soft-hard data fusion model for client credit risk assessment.