Credit scorecards: can machine learning methods enhance the current landscape?

dc.contributor.author	Sekanka, Thapelo
dc.date.accessioned	2023-01-11T08:37:33Z
dc.date.available	2023-01-11T08:37:33Z
dc.date.issued	2022
dc.description	A dissertation submitted in fulfilment of the requirements for the degree of Master of Science to the Faculty of Science, University of the Witwatersrand, 2022
dc.description.abstract	Credit Scoring is a system that generates a credit score for a customer based on their financial behaviour. The higher the score, the more likely it is that the bank will approve the customer’s request for credit. This study investigates a number of different methods that can be used for credit scoring and compares them. The study also assesses the stability of the scorecards by measuring the performance of the scorecard using a dataset that was not part of the development sample. The random forest regression scorecards provide the best relative performance out of all. The scorecards were implemented using a static as well as a dynamic approach. The dynamic approach provides better overall performance for most of the scorecards it allows the scorecards to improve by learning from the data.
dc.description.librarian	TL (2023)
dc.faculty	Faculty of Science
dc.identifier.uri	https://hdl.handle.net/10539/33969
dc.language.iso	en
dc.title	Credit scorecards: can machine learning methods enhance the current landscape?
dc.type	Dissertation

Now showing 1 - 1 of 1

Now showing 1 - 1 of 1