Document Type

Theses, Masters


This item is available under a Creative Commons License for non-commercial use only


Computer Sciences

Publication Details

A dissertation submitted in partial fulflment of the requirements of Technological University Dublin for the degree of M.Sc. in Computing (Data Analytics), March 2016.


This research project investigates the predictive capability of macro-economic features in modelling credit risk for small medium enterprises (SME/SMEs). There have been indications that there is strong correlation between economic growth and the size of the SME sector in an economy. However, since the financial crisis and consequent policies and regulations, SMEs have been hampered in attempts to access credit. It has also been noted that while there is a substantial amount of credit risk literature, there is little research on how macro-economic factors affect credit risk. Being able to improve credit scoring by even a small amount can have a very positive effect on a financial institution's profits, reputation and ability to support the economy. Typically, in the credit scoring process two methods of scoring are carried out, application scoring model and behavioural scoring model. These models for predicting customers who are likely to default usually rely upon financial, demographic and transactional data as the predictive inputs. This research investigates the use of a much coarser source of data at a macro-economic level by a low level and high level regions in Ireland. Features such as level of employment/unemployment, education attainment, consumer spending trends and default levels by different banking products will be evaluated as part of the research project. In the course of this research, techniques and methods are established for evaluating the usefulness of macro-economic features. These are subsequently introduced into the predictive models to be evaluated. It was found that while employing coarse classification and subsequently choosing the macro-economic features with the highest information value in the predictive model, the accuracy across all performance measures improved significantly. This has proven that macro-economic features have the potential to be used in modelling credit risk for SMEs in the future.