The potential of small and medium enterprises (SMEs) in promoting economic growth in both developed and developing countries is widely accepted and documented by both scholars and policy makers. Particularly lacking are studies on the evidence in support of the importance of credit rationing to the sustainability of SMEs in an emerging economy like South Africa’s. This specific problem, especially in the developing countries, has been identified as the major bottleneck in realising socio-economic potentials of SMEs in those countries. However, one of the major ways of addressing the challenge of inadequate funding that exists within the SME sector is the use of bank credit. This study was therefore undertaken to explore the role of commercial banks in the provision of credit to the SMEs in South Africa. This study focuses on the issue of the relationship between the banking industry and SMEs. In particular, the problem of credit rationing of, and discrimination against SMEs by commercial banks was investigated. Because credit rationing and finance gaps can stem from imperfections on either supply-side (banks), or demand-side (SMEs), or both, the intention of the study was to examine both of these variables in order to uncover the implications of their relationships. The empirical analysis is based on survey data collected by means of a structured questionnaire which was distributed amongst banks and SME borrowers in the Gauteng Province of South Africa. Contrary to the general view that commercial banks are disinclined to provide credit to SMEs, the study found that South African banks are keen to serve the SMEs and are therefore making efforts to penetrate this potentially profitable market segment. However, several obstacles are potentially restricting the involvement of banks with SMEs in South Africa. The findings revealed that regulations such as the Financial Intelligence Centre Act (FICA) and the National Credit Act (NCA) came out strongly as major hindrances of bank financing to SMEs. Furthermore, it was shown that compliance with the NCA was ranked higher than credit history and profitability as a factor hindering the approval of SME loans. - iii - However, by using the structural equation modelling (SEM), the results also show that there is a positive and significant influence of lending technology and collateral on the supply of credit to SMEs. Variables such as creditworthiness, collateral and e-banking were found to have a positive and significant impact on the provision of credit to SMEs by commercial banks. For both the supply- and demand-side analysis, technology came out as the most important predictor of SME access to finance. This means that banks should strive to align their lending techniques with the dynamic technological developments so as to reach as many SMEs as possible even in the geographically dispersed regions. It is anticipated that improving SME access to bank credit could be the key to the growth and sustainability of SMEs, the alleviation of poverty and unemployment; and consequently leading to the growth of the South African economy. / Business Management / D. Com. (Business Management)

O presente trabalho apresenta um estudo feito para a elaboração de um modelo de análise de crédito para micro, pequenas e médias empresas (MPME) utilizando Inteligência Artificial. Apresenta, também, uma contribuição de um novo método de raciocínio baseado em casos, denominado FISKNN, que utiliza medida de similaridade presente nos métodos KNN e KNN-Fuzzy, e um sistema de inferência Fuzzy para decidir se a classe de um determinado caso é a classe do elemento mais próximo ou a classe da maioria dos K elementos selecionados para análise. Compara-se o método FISKNN com os métodos tradicionais KNN e KNN-Fuzzy utilizando os dados do Machine Learning Repository da Universidade da Califórnia, e apresentam-se três estudos de casos com bases de dados selecionadas das informações provenientes de solicitações de financiamento através do Cartão BNDES. / This work presents an investigation of a model of credit analysis for micro, small and medium size enterprises based on artificial intelligence techniques. The novelty is a cases-based reasoning, denoted by FISKNN, which uses a measure of similarity present in the KNN and KNN-Fuzzy methods, and a Fuzzy Inference System to decide between the class of the nearest case and the class of the majority of K elements selected for the analysis. One compares the FISKNN methods with the more traditional ones, KNN and KNNFuzzy, using data from the Machine Learning Repository of the University of California, and one presents three study cases with data bases selected from the set of financing applications to the BNDES Card.

O presente trabalho apresenta um estudo feito para a elaboração de um modelo de análise de crédito para micro, pequenas e médias empresas (MPME) utilizando Inteligência Artificial. Apresenta, também, uma contribuição de um novo método de raciocínio baseado em casos, denominado FISKNN, que utiliza medida de similaridade presente nos métodos KNN e KNN-Fuzzy, e um sistema de inferência Fuzzy para decidir se a classe de um determinado caso é a classe do elemento mais próximo ou a classe da maioria dos K elementos selecionados para análise. Compara-se o método FISKNN com os métodos tradicionais KNN e KNN-Fuzzy utilizando os dados do Machine Learning Repository da Universidade da Califórnia, e apresentam-se três estudos de casos com bases de dados selecionadas das informações provenientes de solicitações de financiamento através do Cartão BNDES. / This work presents an investigation of a model of credit analysis for micro, small and medium size enterprises based on artificial intelligence techniques. The novelty is a cases-based reasoning, denoted by FISKNN, which uses a measure of similarity present in the KNN and KNN-Fuzzy methods, and a Fuzzy Inference System to decide between the class of the nearest case and the class of the majority of K elements selected for the analysis. One compares the FISKNN methods with the more traditional ones, KNN and KNNFuzzy, using data from the Machine Learning Repository of the University of California, and one presents three study cases with data bases selected from the set of financing applications to the BNDES Card.