Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035423859> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3035423859 endingPage "191649" @default.
- W3035423859 startingPage "191649" @default.
- W3035423859 abstract "Logistic regression (LR) and support vector machine algorithms, together with linear and nonlinear deep neural networks (DNNs), are applied to lending data in order to replicate lender acceptance of loans and predict the likelihood of default of issued loans. A two-phase model is proposed; the first phase predicts loan rejection, while the second one predicts default risk for approved loans. LR was found to be the best performer for the first phase, with test set recall macro score of <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mn>77.4</mml:mn> <mml:mtext>%</mml:mtext> </mml:math> . DNNs were applied to the second phase only, where they achieved best performance, with test set recall score of <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mn>72</mml:mn> <mml:mtext>%</mml:mtext> </mml:math> , for defaults. This shows that artificial intelligence can improve current credit risk models reducing the default risk of issued loans by as much as <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mn>70</mml:mn> <mml:mtext>%</mml:mtext> </mml:math> . The models were also applied to loans taken for small businesses alone. The first phase of the model performs significantly better when trained on the whole dataset. Instead, the second phase performs significantly better when trained on the small business subset. This suggests a potential discrepancy between how these loans are screened and how they should be analysed in terms of default prediction." @default.
- W3035423859 created "2020-06-19" @default.
- W3035423859 creator A5009186562 @default.
- W3035423859 creator A5050674002 @default.
- W3035423859 date "2020-06-01" @default.
- W3035423859 modified "2023-10-02" @default.
- W3035423859 title "Peer-to-peer loan acceptance and default prediction with artificial intelligence" @default.
- W3035423859 cites W1995308800 @default.
- W3035423859 cites W2004915807 @default.
- W3035423859 cites W2008056655 @default.
- W3035423859 cites W2076063813 @default.
- W3035423859 cites W2094688862 @default.
- W3035423859 cites W2113287505 @default.
- W3035423859 cites W2122825543 @default.
- W3035423859 cites W2138144286 @default.
- W3035423859 cites W2155653793 @default.
- W3035423859 cites W2162397980 @default.
- W3035423859 cites W2185712725 @default.
- W3035423859 cites W2498119267 @default.
- W3035423859 cites W2594265094 @default.
- W3035423859 cites W2793452328 @default.
- W3035423859 cites W3104660771 @default.
- W3035423859 cites W3124284538 @default.
- W3035423859 doi "https://doi.org/10.1098/rsos.191649" @default.
- W3035423859 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7353984" @default.
- W3035423859 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32742678" @default.
- W3035423859 hasPublicationYear "2020" @default.
- W3035423859 type Work @default.
- W3035423859 sameAs 3035423859 @default.
- W3035423859 citedByCount "20" @default.
- W3035423859 countsByYear W30354238592020 @default.
- W3035423859 countsByYear W30354238592021 @default.
- W3035423859 countsByYear W30354238592022 @default.
- W3035423859 countsByYear W30354238592023 @default.
- W3035423859 crossrefType "journal-article" @default.
- W3035423859 hasAuthorship W3035423859A5009186562 @default.
- W3035423859 hasAuthorship W3035423859A5050674002 @default.
- W3035423859 hasBestOaLocation W30354238591 @default.
- W3035423859 hasConcept C10138342 @default.
- W3035423859 hasConcept C11413529 @default.
- W3035423859 hasConcept C119857082 @default.
- W3035423859 hasConcept C12267149 @default.
- W3035423859 hasConcept C151956035 @default.
- W3035423859 hasConcept C154945302 @default.
- W3035423859 hasConcept C162324750 @default.
- W3035423859 hasConcept C169903167 @default.
- W3035423859 hasConcept C177264268 @default.
- W3035423859 hasConcept C199360897 @default.
- W3035423859 hasConcept C2777764128 @default.
- W3035423859 hasConcept C41008148 @default.
- W3035423859 hasConcept C50644808 @default.
- W3035423859 hasConcept C58489278 @default.
- W3035423859 hasConceptScore W3035423859C10138342 @default.
- W3035423859 hasConceptScore W3035423859C11413529 @default.
- W3035423859 hasConceptScore W3035423859C119857082 @default.
- W3035423859 hasConceptScore W3035423859C12267149 @default.
- W3035423859 hasConceptScore W3035423859C151956035 @default.
- W3035423859 hasConceptScore W3035423859C154945302 @default.
- W3035423859 hasConceptScore W3035423859C162324750 @default.
- W3035423859 hasConceptScore W3035423859C169903167 @default.
- W3035423859 hasConceptScore W3035423859C177264268 @default.
- W3035423859 hasConceptScore W3035423859C199360897 @default.
- W3035423859 hasConceptScore W3035423859C2777764128 @default.
- W3035423859 hasConceptScore W3035423859C41008148 @default.
- W3035423859 hasConceptScore W3035423859C50644808 @default.
- W3035423859 hasConceptScore W3035423859C58489278 @default.
- W3035423859 hasFunder F4320320300 @default.
- W3035423859 hasIssue "6" @default.
- W3035423859 hasLocation W30354238591 @default.
- W3035423859 hasLocation W30354238592 @default.
- W3035423859 hasLocation W30354238593 @default.
- W3035423859 hasLocation W30354238594 @default.
- W3035423859 hasLocation W30354238595 @default.
- W3035423859 hasOpenAccess W3035423859 @default.
- W3035423859 hasPrimaryLocation W30354238591 @default.
- W3035423859 hasRelatedWork W1996541855 @default.
- W3035423859 hasRelatedWork W2123376283 @default.
- W3035423859 hasRelatedWork W2554948173 @default.
- W3035423859 hasRelatedWork W3099765033 @default.
- W3035423859 hasRelatedWork W3195168932 @default.
- W3035423859 hasRelatedWork W3201070945 @default.
- W3035423859 hasRelatedWork W4316658362 @default.
- W3035423859 hasRelatedWork W4321636153 @default.
- W3035423859 hasRelatedWork W4383535405 @default.
- W3035423859 hasRelatedWork W4384828018 @default.
- W3035423859 hasVolume "7" @default.
- W3035423859 isParatext "false" @default.
- W3035423859 isRetracted "false" @default.
- W3035423859 magId "3035423859" @default.
- W3035423859 workType "article" @default.