Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362581811> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4362581811 endingPage "221" @default.
- W4362581811 startingPage "221" @default.
- W4362581811 abstract "Predicting creditworthiness is an important task in the banking industry, as it allows banks to make informed lending decisions and manage risk. In this paper, we investigate the performance of two different deep learning credit scoring models developed on the textual descriptions of customer transactions available from open banking APIs. The first model is a deep learning model trained from scratch, while the second model uses transfer learning with a multilingual BERT model. We evaluate the predictive performance of these models using the area under the receiver operating characteristic curve (AUC) and Brier score. We find that a deep learning model trained from scratch outperforms a BERT transformer model finetuned on the same data. Furthermore, we find that SHAP can be used to explain such models both on a global level and for explaining rejections of actual applications." @default.
- W4362581811 created "2023-04-06" @default.
- W4362581811 creator A5031314987 @default.
- W4362581811 creator A5063385498 @default.
- W4362581811 date "2023-04-02" @default.
- W4362581811 modified "2023-10-16" @default.
- W4362581811 title "Explaining Deep Learning Models for Credit Scoring with SHAP: A Case Study Using Open Banking Data" @default.
- W4362581811 cites W1787224781 @default.
- W4362581811 cites W1982120517 @default.
- W4362581811 cites W2005510983 @default.
- W4362581811 cites W2053790618 @default.
- W4362581811 cites W2073241381 @default.
- W4362581811 cites W2093829413 @default.
- W4362581811 cites W2128272608 @default.
- W4362581811 cites W2131816657 @default.
- W4362581811 cites W2168123127 @default.
- W4362581811 cites W2748025215 @default.
- W4362581811 cites W2765793020 @default.
- W4362581811 cites W2787468747 @default.
- W4362581811 cites W2790611518 @default.
- W4362581811 cites W2891503716 @default.
- W4362581811 cites W2897596136 @default.
- W4362581811 cites W2919115771 @default.
- W4362581811 cites W2963026768 @default.
- W4362581811 cites W3012625840 @default.
- W4362581811 cites W3034350582 @default.
- W4362581811 cites W3121477658 @default.
- W4362581811 cites W3128513378 @default.
- W4362581811 cites W3135286407 @default.
- W4362581811 cites W3146613606 @default.
- W4362581811 cites W4200176036 @default.
- W4362581811 cites W4206740101 @default.
- W4362581811 cites W4312127937 @default.
- W4362581811 cites W4313159534 @default.
- W4362581811 doi "https://doi.org/10.3390/jrfm16040221" @default.
- W4362581811 hasPublicationYear "2023" @default.
- W4362581811 type Work @default.
- W4362581811 citedByCount "0" @default.
- W4362581811 crossrefType "journal-article" @default.
- W4362581811 hasAuthorship W4362581811A5031314987 @default.
- W4362581811 hasAuthorship W4362581811A5063385498 @default.
- W4362581811 hasBestOaLocation W43625818111 @default.
- W4362581811 hasConcept C108583219 @default.
- W4362581811 hasConcept C111919701 @default.
- W4362581811 hasConcept C119857082 @default.
- W4362581811 hasConcept C121332964 @default.
- W4362581811 hasConcept C148524875 @default.
- W4362581811 hasConcept C150899416 @default.
- W4362581811 hasConcept C154945302 @default.
- W4362581811 hasConcept C162324750 @default.
- W4362581811 hasConcept C165801399 @default.
- W4362581811 hasConcept C187736073 @default.
- W4362581811 hasConcept C2780451532 @default.
- W4362581811 hasConcept C2781235140 @default.
- W4362581811 hasConcept C35405484 @default.
- W4362581811 hasConcept C41008148 @default.
- W4362581811 hasConcept C62520636 @default.
- W4362581811 hasConcept C66322947 @default.
- W4362581811 hasConceptScore W4362581811C108583219 @default.
- W4362581811 hasConceptScore W4362581811C111919701 @default.
- W4362581811 hasConceptScore W4362581811C119857082 @default.
- W4362581811 hasConceptScore W4362581811C121332964 @default.
- W4362581811 hasConceptScore W4362581811C148524875 @default.
- W4362581811 hasConceptScore W4362581811C150899416 @default.
- W4362581811 hasConceptScore W4362581811C154945302 @default.
- W4362581811 hasConceptScore W4362581811C162324750 @default.
- W4362581811 hasConceptScore W4362581811C165801399 @default.
- W4362581811 hasConceptScore W4362581811C187736073 @default.
- W4362581811 hasConceptScore W4362581811C2780451532 @default.
- W4362581811 hasConceptScore W4362581811C2781235140 @default.
- W4362581811 hasConceptScore W4362581811C35405484 @default.
- W4362581811 hasConceptScore W4362581811C41008148 @default.
- W4362581811 hasConceptScore W4362581811C62520636 @default.
- W4362581811 hasConceptScore W4362581811C66322947 @default.
- W4362581811 hasFunder F4320323299 @default.
- W4362581811 hasIssue "4" @default.
- W4362581811 hasLocation W43625818111 @default.
- W4362581811 hasOpenAccess W4362581811 @default.
- W4362581811 hasPrimaryLocation W43625818111 @default.
- W4362581811 hasRelatedWork W2960456850 @default.
- W4362581811 hasRelatedWork W3031818154 @default.
- W4362581811 hasRelatedWork W3133293092 @default.
- W4362581811 hasRelatedWork W3166467183 @default.
- W4362581811 hasRelatedWork W4213299466 @default.
- W4362581811 hasRelatedWork W4281382123 @default.
- W4362581811 hasRelatedWork W4312200629 @default.
- W4362581811 hasRelatedWork W4318834068 @default.
- W4362581811 hasRelatedWork W4318957922 @default.
- W4362581811 hasRelatedWork W4362581811 @default.
- W4362581811 hasVolume "16" @default.
- W4362581811 isParatext "false" @default.
- W4362581811 isRetracted "false" @default.
- W4362581811 workType "article" @default.