FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285596328> ?p ?o ?g. }

• W4285596328 endingPage "1690" @default.
• W4285596328 startingPage "1669" @default.
• W4285596328 abstract "Abstract Online consumer lending has recently been growing rapidly, but it faces high credit risk. For this problem, developing powerful credit scoring models has become an effective solution and can be achieved from three aspects: modeling approach, data source, and evaluation measure. This paper proposes a novel model that departs from those in previous studies in threefold. First, a heterogeneous deep forest model that combines deep learning architecture and tree‐based ensemble classifiers is proposed as the modeling approach. Second, a Bayesian‐based macroeconomic variable optimization method is developed to determine the macroeconomic variables and the corresponding lag term, and the selected macroeconomic variables are used as supplementary data source for modeling. Lastly, a series of capital charge error measures is proposed to evaluate credit scoring models from a regulatory perspective. The proposal is evaluated on multiple large datasets under performance measures on predictive accuracy, profitability, and capital charge errors. Frequentist and Bayesian nonparametric significance tests are used to examine the statistical significance of heterogeneous deep forest and benchmarks. Three main conclusions can be reached from the comparison. First, heterogeneous deep forest significantly outperforms the industry benchmarks over all the evaluation measures. Second, the predictive performance is enhanced after incorporating the selected macroeconomic variables and the corresponding lag, and the result remains robust under cross‐validation and forward‐chaining validation. Third, the capital charge errors reflect the model performance from a regulatory perspective and thus lead to different rankings from those when evaluating predictive accuracy and profitability." @default.
• W4285596328 created "2022-07-16" @default.
• W4285596328 creator A5015231158 @default.
• W4285596328 creator A5045824104 @default.
• W4285596328 creator A5053890256 @default.
• W4285596328 creator A5057946457 @default.
• W4285596328 creator A5089725500 @default.
• W4285596328 date "2022-07-20" @default.
• W4285596328 modified "2023-10-18" @default.
• W4285596328 title "Deep learning meets decision trees: An application of a heterogeneous deep forest approach in credit scoring for online consumer lending" @default.
• W4285596328 cites W1584288932 @default.
• W4285596328 cites W1678356000 @default.
• W4285596328 cites W1968023063 @default.
• W4285596328 cites W1977009091 @default.
• W4285596328 cites W1980770954 @default.
• W4285596328 cites W1984104714 @default.
• W4285596328 cites W1992958333 @default.
• W4285596328 cites W2015768982 @default.
• W4285596328 cites W2018188846 @default.
• W4285596328 cites W2054637737 @default.
• W4285596328 cites W2056132907 @default.
• W4285596328 cites W2098738227 @default.
• W4285596328 cites W2131816657 @default.
• W4285596328 cites W2137959503 @default.
• W4285596328 cites W2151554678 @default.
• W4285596328 cites W2163504005 @default.
• W4285596328 cites W2165466912 @default.
• W4285596328 cites W2189149359 @default.
• W4285596328 cites W2336505047 @default.
• W4285596328 cites W2473172823 @default.
• W4285596328 cites W2556216749 @default.
• W4285596328 cites W2586297576 @default.
• W4285596328 cites W2603785580 @default.
• W4285596328 cites W2700766797 @default.
• W4285596328 cites W2761700016 @default.
• W4285596328 cites W2782788926 @default.
• W4285596328 cites W2783336591 @default.
• W4285596328 cites W2788597170 @default.
• W4285596328 cites W2792920075 @default.
• W4285596328 cites W2793304295 @default.
• W4285596328 cites W2799791930 @default.
• W4285596328 cites W2803273200 @default.
• W4285596328 cites W2803388689 @default.
• W4285596328 cites W2885794594 @default.
• W4285596328 cites W2887420687 @default.
• W4285596328 cites W2887596728 @default.
• W4285596328 cites W2888997571 @default.
• W4285596328 cites W2891295587 @default.
• W4285596328 cites W2896796252 @default.
• W4285596328 cites W2898234524 @default.
• W4285596328 cites W2904485001 @default.
• W4285596328 cites W2905025229 @default.
• W4285596328 cites W2911964244 @default.
• W4285596328 cites W2921397903 @default.
• W4285596328 cites W2966139567 @default.
• W4285596328 cites W2970989889 @default.
• W4285596328 cites W2989599764 @default.
• W4285596328 cites W2998458143 @default.
• W4285596328 cites W3009609110 @default.
• W4285596328 cites W3013460382 @default.
• W4285596328 cites W3018637877 @default.
• W4285596328 cites W3021074122 @default.
• W4285596328 cites W3025393226 @default.
• W4285596328 cites W3028645543 @default.
• W4285596328 cites W3044323082 @default.
• W4285596328 cites W3048715644 @default.
• W4285596328 cites W3094559308 @default.
• W4285596328 cites W3095606640 @default.
• W4285596328 cites W3102476541 @default.
• W4285596328 cites W3112123599 @default.
• W4285596328 cites W3124122197 @default.
• W4285596328 cites W3124625789 @default.
• W4285596328 cites W3135286407 @default.
• W4285596328 cites W3163978125 @default.
• W4285596328 cites W3172236574 @default.
• W4285596328 cites W3201341859 @default.
• W4285596328 cites W3216660050 @default.
• W4285596328 cites W4232478844 @default.
• W4285596328 cites W4232714830 @default.
• W4285596328 doi "https://doi.org/10.1002/for.2891" @default.
• W4285596328 hasPublicationYear "2022" @default.
• W4285596328 type Work @default.
• W4285596328 citedByCount "3" @default.
• W4285596328 countsByYear W42855963282022 @default.
• W4285596328 countsByYear W42855963282023 @default.
• W4285596328 crossrefType "journal-article" @default.
• W4285596328 hasAuthorship W4285596328A5015231158 @default.
• W4285596328 hasAuthorship W4285596328A5045824104 @default.
• W4285596328 hasAuthorship W4285596328A5053890256 @default.
• W4285596328 hasAuthorship W4285596328A5057946457 @default.
• W4285596328 hasAuthorship W4285596328A5089725500 @default.
• W4285596328 hasConcept C10138342 @default.
• W4285596328 hasConcept C107673813 @default.
• W4285596328 hasConcept C108583219 @default.
• W4285596328 hasConcept C119857082 @default.
• W4285596328 hasConcept C124101348 @default.
• W4285596328 hasConcept C129361004 @default.
• W4285596328 hasConcept C149782125 @default.

• next