Predicting Credit Worthiness in Retail Banking with Limited Scoring Data.
Financial intermediaries are the key contributor in the economy of Zimbabwe as they provide financial services for the nation. This study focused on predicting creditworthiness in retail banking with limited scoring data from 2009 to 2017. To gather the empirical data interviews with loan officers of 10 commercial banks in Bulawayo were done also questionnaires were issued to respondents using convenience sampling around the Bulawayo CBD so as to gather information to use when creating a scoring model. An experimental research design was adopted so as to predict what the outcome will be. Logistic regression was used to establish a relationship between the dependent and independent variables so as to come up with a model suitable to measure the credit score of an individual. Variables used in the model were gender, age, income level, residential status and employment status. The study found out that the variables used in the model are very significant meaning that if one gets score of 0.5 and above they do qualify for a loan and a score below that they do not qualify for a loan, also gender was dropped out of the model due to the fact that it is not significant and it does not affect the calculation of a credit score. This study also proved that there should be little or no correlation between variables as this can affect the results of a study if multi-collinearity is present within the independent variables. In light of these findings the study recommends that more studies should be done on this study no only focusing on one geographical regions others should be considered also include microfinance companies so as to find out how they operate.