FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205653380> ?p ?o ?g. }

• W3205653380 endingPage "106334" @default.
• W3205653380 startingPage "106334" @default.
• W3205653380 abstract "We extend the linear quantile regression with a neural network structure to enable more flexibility in every quantile of the bank loan loss given default distribution. This allows us to model interactions and non-linear impacts of any kind without the need of specifying the exact form beforehand. The precision of the quantile forecasts increases up to 30% compared to the benchmark, especially for higher quantiles which are most important in credit risk. By using a novel feature importance measure, we calculate the strength, direction, interactions and other non-linear impacts for every conditional quantile and every variable. This enables us to explain why our extension exhibits superior performance over the benchmark. Moreover, we find that the macroeconomy is up to two times more important in USA than in Europe and has large joint impacts in both regions. The macroeconomy is most important in the US, whereas in Europe collateralization is essential." @default.
• W3205653380 created "2021-10-25" @default.
• W3205653380 creator A5019139847 @default.
• W3205653380 creator A5082382938 @default.
• W3205653380 creator A5090037535 @default.
• W3205653380 date "2022-01-01" @default.
• W3205653380 modified "2023-10-14" @default.
• W3205653380 title "Opening the black box – Quantile neural networks for loss given default prediction" @default.
• W3205653380 cites W1498436455 @default.
• W3205653380 cites W1678356000 @default.
• W3205653380 cites W1970242716 @default.
• W3205653380 cites W1970739592 @default.
• W3205653380 cites W1977007832 @default.
• W3205653380 cites W1988115241 @default.
• W3205653380 cites W1988981281 @default.
• W3205653380 cites W2011416863 @default.
• W3205653380 cites W2018730525 @default.
• W3205653380 cites W2021091247 @default.
• W3205653380 cites W2031339922 @default.
• W3205653380 cites W2043077358 @default.
• W3205653380 cites W2046024388 @default.
• W3205653380 cites W2046033161 @default.
• W3205653380 cites W2077372486 @default.
• W3205653380 cites W2091687672 @default.
• W3205653380 cites W2103496339 @default.
• W3205653380 cites W2125847307 @default.
• W3205653380 cites W2126147689 @default.
• W3205653380 cites W2133479700 @default.
• W3205653380 cites W2142282274 @default.
• W3205653380 cites W2154948784 @default.
• W3205653380 cites W2410388316 @default.
• W3205653380 cites W2510538700 @default.
• W3205653380 cites W2591768545 @default.
• W3205653380 cites W2606087171 @default.
• W3205653380 cites W2613872131 @default.
• W3205653380 cites W2678892993 @default.
• W3205653380 cites W2737373287 @default.
• W3205653380 cites W2756159573 @default.
• W3205653380 cites W2785163911 @default.
• W3205653380 cites W2790611518 @default.
• W3205653380 cites W2791531554 @default.
• W3205653380 cites W2804101929 @default.
• W3205653380 cites W2806986051 @default.
• W3205653380 cites W2897596136 @default.
• W3205653380 cites W2942670250 @default.
• W3205653380 cites W2943209351 @default.
• W3205653380 cites W2946130033 @default.
• W3205653380 cites W2957138180 @default.
• W3205653380 cites W2964305932 @default.
• W3205653380 cites W2966027283 @default.
• W3205653380 cites W2969209099 @default.
• W3205653380 cites W2970649545 @default.
• W3205653380 cites W2983772261 @default.
• W3205653380 cites W2997325425 @default.
• W3205653380 cites W3005631642 @default.
• W3205653380 cites W3007883824 @default.
• W3205653380 cites W3035517615 @default.
• W3205653380 cites W3084402488 @default.
• W3205653380 cites W3122617352 @default.
• W3205653380 cites W3124149074 @default.
• W3205653380 cites W3124149353 @default.
• W3205653380 cites W3125011771 @default.
• W3205653380 cites W3130411973 @default.
• W3205653380 cites W4205539948 @default.
• W3205653380 cites W4241653265 @default.
• W3205653380 doi "https://doi.org/10.1016/j.jbankfin.2021.106334" @default.
• W3205653380 hasPublicationYear "2022" @default.
• W3205653380 type Work @default.
• W3205653380 sameAs 3205653380 @default.
• W3205653380 citedByCount "12" @default.
• W3205653380 countsByYear W32056533802021 @default.
• W3205653380 countsByYear W32056533802022 @default.
• W3205653380 countsByYear W32056533802023 @default.
• W3205653380 crossrefType "journal-article" @default.
• W3205653380 hasAuthorship W3205653380A5019139847 @default.
• W3205653380 hasAuthorship W3205653380A5082382938 @default.
• W3205653380 hasAuthorship W3205653380A5090037535 @default.
• W3205653380 hasConcept C105795698 @default.
• W3205653380 hasConcept C118671147 @default.
• W3205653380 hasConcept C13280743 @default.
• W3205653380 hasConcept C133930124 @default.
• W3205653380 hasConcept C149782125 @default.
• W3205653380 hasConcept C154945302 @default.
• W3205653380 hasConcept C162324750 @default.
• W3205653380 hasConcept C175444787 @default.
• W3205653380 hasConcept C185798385 @default.
• W3205653380 hasConcept C205649164 @default.
• W3205653380 hasConcept C2780598303 @default.
• W3205653380 hasConcept C2864544 @default.
• W3205653380 hasConcept C29122968 @default.
• W3205653380 hasConcept C33923547 @default.
• W3205653380 hasConcept C41008148 @default.
• W3205653380 hasConcept C50644808 @default.
• W3205653380 hasConcept C63817138 @default.
• W3205653380 hasConcept C94966114 @default.
• W3205653380 hasConceptScore W3205653380C105795698 @default.
• W3205653380 hasConceptScore W3205653380C118671147 @default.
• W3205653380 hasConceptScore W3205653380C13280743 @default.

• next