Vis enkel innførsel

dc.contributor.authorHovdenakk, Arne Hesjedal
dc.date.accessioned2021-06-30T23:56:26Z
dc.date.available2021-06-30T23:56:26Z
dc.date.issued2021-06-15
dc.date.submitted2021-06-30T22:00:52Z
dc.identifier.urihttps://hdl.handle.net/11250/2762661
dc.description.abstractIn this thesis, I compare logistic regression to the machine learning models k-nearest neighbor, decision trees, random forest, and gradient booster by creating different credit models. By using data from an anonymous Norwegian bank for consumer loan borrowers, I compare the models when continuous variables are split into intervals by using weight of evidence, and when they are kept in their raw form. By using Area under Receiver Operating Characteristic (AUROC) and Brier score as performance measures, I find that logistic regression and gradient booster are the most accurate models for this dataset, and logistic regression is recommended because of its interpretability.
dc.language.isoeng
dc.publisherThe University of Bergen
dc.rightsCopyright the Author. All rights reserved
dc.subjectcredit scoring
dc.subjectlogistic regression.
dc.subjectMachine learning
dc.titleMachine learning vs logistic regression in credit scoring: A trade-off between accuracy and interpretability?
dc.typeMaster thesis
dc.date.updated2021-06-30T22:00:52Z
dc.rights.holderCopyright the Author. All rights reserved
dc.description.degreeMasteroppgave
dc.description.localcodeECON391
dc.description.localcodeMASV-SØK
dc.description.localcodePROF-SØK
dc.subject.nus734103
fs.subjectcodeECON391
fs.unitcode15-15-0


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel