FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148119887> ?p ?o ?g. }

• W3148119887 endingPage "50440" @default.
• W3148119887 startingPage "50426" @default.
• W3148119887 abstract "Credit scoring has become an important risk management tool for money lending institutions. Over the years, statistical and classical machine learning models have been the most researched risk management tools in credit scoring literature, and recently the focus has turned to deep learning models. This transition is due to better performances that are shown by deep learning models in different domains. Despite deep learning models' superior performances, there is still a need for explaining how these models make their predictions. The non-transparency nature of deep learning models has created a bottleneck for their use in credit scoring. Explanations of decisions are important for lending institutions since it is a requirement for automated decisions that are generated by non-transparent models to be explained. The other issue in using deep learning models, specifically 2D Convolutional Neural Networks (CNNs), in credit scoring is the need to have the data in image format. We propose an explainable deep learning model for credit scoring which can harness the performance benefits offered by deep learning and yet comply with the legislation requirements for the automated decision-making processes. The proposed method converts tabular datasets into images and thus allowing the application of 2D CNNs in credit scoring. Each pixel of the image corresponds to a feature bin of the tabular dataset. The predictions from the 2D CNNs were explained using state-of-the-art explanation methods. Furthermore, explanations were evaluated using a sanity check methodology and also performances of the explanation methods were compared quantitatively. The proposed explainable deep learning model outperforms the other credit scoring methods on publicly available credit scoring datasets." @default.
• W3148119887 created "2021-04-13" @default.
• W3148119887 creator A5049945687 @default.
• W3148119887 creator A5059788672 @default.
• W3148119887 date "2021-01-01" @default.
• W3148119887 modified "2023-10-17" @default.
• W3148119887 title "Making Deep Learning-Based Predictions for Credit Scoring Explainable" @default.
• W3148119887 cites W1608477047 @default.
• W3148119887 cites W1998492739 @default.
• W3148119887 cites W2073241381 @default.
• W3148119887 cites W2084341220 @default.
• W3148119887 cites W2093829413 @default.
• W3148119887 cites W2137959503 @default.
• W3148119887 cites W2147800946 @default.
• W3148119887 cites W2336505047 @default.
• W3148119887 cites W2336631262 @default.
• W3148119887 cites W2516809705 @default.
• W3148119887 cites W2586297576 @default.
• W3148119887 cites W2767466046 @default.
• W3148119887 cites W2787117672 @default.
• W3148119887 cites W2787468747 @default.
• W3148119887 cites W2792224072 @default.
• W3148119887 cites W2811423659 @default.
• W3148119887 cites W2892112674 @default.
• W3148119887 cites W2945976633 @default.
• W3148119887 cites W2962858109 @default.
• W3148119887 cites W2963041618 @default.
• W3148119887 cites W2963847595 @default.
• W3148119887 cites W2964296212 @default.
• W3148119887 cites W2965914043 @default.
• W3148119887 cites W2972441196 @default.
• W3148119887 cites W2997654184 @default.
• W3148119887 cites W3000716014 @default.
• W3148119887 cites W3013460382 @default.
• W3148119887 cites W3014660692 @default.
• W3148119887 cites W3090418931 @default.
• W3148119887 cites W3121438481 @default.
• W3148119887 doi "https://doi.org/10.1109/access.2021.3068854" @default.
• W3148119887 hasPublicationYear "2021" @default.
• W3148119887 type Work @default.
• W3148119887 sameAs 3148119887 @default.
• W3148119887 citedByCount "19" @default.
• W3148119887 countsByYear W31481198872022 @default.
• W3148119887 countsByYear W31481198872023 @default.
• W3148119887 crossrefType "journal-article" @default.
• W3148119887 hasAuthorship W3148119887A5049945687 @default.
• W3148119887 hasAuthorship W3148119887A5059788672 @default.
• W3148119887 hasBestOaLocation W31481198871 @default.
• W3148119887 hasConcept C10138342 @default.
• W3148119887 hasConcept C108583219 @default.
• W3148119887 hasConcept C119857082 @default.
• W3148119887 hasConcept C136764020 @default.
• W3148119887 hasConcept C145097563 @default.
• W3148119887 hasConcept C149635348 @default.
• W3148119887 hasConcept C154945302 @default.
• W3148119887 hasConcept C162324750 @default.
• W3148119887 hasConcept C178350159 @default.
• W3148119887 hasConcept C2778827112 @default.
• W3148119887 hasConcept C2780513914 @default.
• W3148119887 hasConcept C2780747020 @default.
• W3148119887 hasConcept C2983355114 @default.
• W3148119887 hasConcept C41008148 @default.
• W3148119887 hasConcept C81363708 @default.
• W3148119887 hasConceptScore W3148119887C10138342 @default.
• W3148119887 hasConceptScore W3148119887C108583219 @default.
• W3148119887 hasConceptScore W3148119887C119857082 @default.
• W3148119887 hasConceptScore W3148119887C136764020 @default.
• W3148119887 hasConceptScore W3148119887C145097563 @default.
• W3148119887 hasConceptScore W3148119887C149635348 @default.
• W3148119887 hasConceptScore W3148119887C154945302 @default.
• W3148119887 hasConceptScore W3148119887C162324750 @default.
• W3148119887 hasConceptScore W3148119887C178350159 @default.
• W3148119887 hasConceptScore W3148119887C2778827112 @default.
• W3148119887 hasConceptScore W3148119887C2780513914 @default.
• W3148119887 hasConceptScore W3148119887C2780747020 @default.
• W3148119887 hasConceptScore W3148119887C2983355114 @default.
• W3148119887 hasConceptScore W3148119887C41008148 @default.
• W3148119887 hasConceptScore W3148119887C81363708 @default.
• W3148119887 hasLocation W31481198871 @default.
• W3148119887 hasLocation W31481198872 @default.
• W3148119887 hasOpenAccess W3148119887 @default.
• W3148119887 hasPrimaryLocation W31481198871 @default.
• W3148119887 hasRelatedWork W2230049528 @default.
• W3148119887 hasRelatedWork W2965782936 @default.
• W3148119887 hasRelatedWork W2970146637 @default.
• W3148119887 hasRelatedWork W2971936868 @default.
• W3148119887 hasRelatedWork W3098273717 @default.
• W3148119887 hasRelatedWork W4213066734 @default.
• W3148119887 hasRelatedWork W4285788677 @default.
• W3148119887 hasRelatedWork W4288356251 @default.
• W3148119887 hasRelatedWork W4294192778 @default.
• W3148119887 hasRelatedWork W4384158267 @default.
• W3148119887 hasVolume "9" @default.
• W3148119887 isParatext "false" @default.
• W3148119887 isRetracted "false" @default.
• W3148119887 magId "3148119887" @default.
• W3148119887 workType "article" @default.