Explaining neural networks used for modeling credit risk

Simple item page
dc.contributor.advisorVisser, Willemen_ZA
dc.contributor.advisorHerbst, B. M.en_ZA
dc.contributor.advisorHoffman, McEloryen_ZA
dc.contributor.authorMohamed, Zhunaiden_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Mathematical Sciences. Division Computer Science.en_ZA
dc.date.accessioned2021-03-04T19:59:51Z
dc.date.accessioned2021-04-21T14:41:11Z
dc.date.available2021-03-04T19:59:51Z
dc.date.available2021-04-21T14:41:11Z
dc.date.issued2021-03
dc.descriptionThesis(MSc.)--Stellenbosch University, 2021.en_ZA
dc.description.abstractENGLISH ABSTRACT: Calculating risk before providing loans is a common problem that credit companies face. The most common solution is credit employees manually assessing the risk of a client by reviewing their credit portfolios. This can be a slow process and is prone to human error. Recently credit companies have been adopting machine learning techniques in order to automate this process, however this has been limited to linear techniques due to interpretability being a strict requirement. Neural networks could provide significant improvements to the way credit risk is modeled, however these are still seen as black boxes. In this work we compare various techniques which claim to provide interpretability into these black boxes. We also use these techniques to provide explanations on a neural network trained on credit data that has been provided to us.en_ZA
dc.description.sponsorshipThe financial assistance of the National Research Foundation(NRF) towards this research is hereby ac- knowledged. Opinions expressed and conclusions arrived at, are those of the author and are not necessarily to be attributed to the NRF.en_ZA
dc.description.versionMastersen_ZA
dc.format.extentxi, 104 pages : illustrationsen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/110117
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectUCTD
dc.subjectMachine Learningen_ZA
dc.subjectNeural networks (Computer science)en_ZA
dc.subjectCredit control -- Automationen_ZA
dc.titleExplaining neural networks used for modeling credit risken_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
mohamed_neural_2021.pdf
Size:
3.86 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description:
Download
Collections
Masters Degrees (Computer Science)