FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285089594> ?p ?o ?g. }

• W4285089594 abstract "Abstract Implementing new machine learning (ML) algorithms for credit default prediction is associated with better predictive performance; however, it also generates new model risks, particularly concerning the supervisory validation process. Recent industry surveys often mention that uncertainty about how supervisors might assess these risks could be a barrier to innovation. In this study, we propose a new framework to quantify model risk-adjustments to compare the performance of several ML methods. To address this challenge, we first harness the internal ratings-based approach to identify up to 13 risk components that we classify into 3 main categories—statistics, technology, and market conduct. Second, to evaluate the importance of each risk category, we collect a series of regulatory documents related to three potential use cases—regulatory capital, credit scoring, or provisioning—and we compute the weight of each category according to the intensity of their mentions, using natural language processing and a risk terminology based on expert knowledge. Finally, we test our framework using popular ML models in credit risk, and a publicly available database, to quantify some proxies of a subset of risk factors that we deem representative. We measure the statistical risk according to the number of hyperparameters and the stability of the predictions. The technological risk is assessed through the transparency of the algorithm and the latency of the ML training method, while the market conduct risk is quantified by the time it takes to run a post hoc technique (SHapley Additive exPlanations) to interpret the output." @default.
• W4285089594 created "2022-07-14" @default.
• W4285089594 creator A5035662031 @default.
• W4285089594 creator A5061104415 @default.
• W4285089594 date "2022-07-12" @default.
• W4285089594 modified "2023-10-06" @default.
• W4285089594 title "Measuring the model risk-adjusted performance of machine learning algorithms in credit default prediction" @default.
• W4285089594 cites W1964159032 @default.
• W4285089594 cites W1964346230 @default.
• W4285089594 cites W2029538739 @default.
• W4285089594 cites W2052611008 @default.
• W4285089594 cites W2084341220 @default.
• W4285089594 cites W2098734551 @default.
• W4285089594 cites W2160660844 @default.
• W4285089594 cites W2282821441 @default.
• W4285089594 cites W2753622376 @default.
• W4285089594 cites W2770743945 @default.
• W4285089594 cites W2775561085 @default.
• W4285089594 cites W2790611518 @default.
• W4285089594 cites W2794772509 @default.
• W4285089594 cites W2807909115 @default.
• W4285089594 cites W2898694742 @default.
• W4285089594 cites W2943467878 @default.
• W4285089594 cites W2945976633 @default.
• W4285089594 cites W2963751193 @default.
• W4285089594 cites W2963809228 @default.
• W4285089594 cites W2964305932 @default.
• W4285089594 cites W2965161792 @default.
• W4285089594 cites W2967730222 @default.
• W4285089594 cites W2969293349 @default.
• W4285089594 cites W2972296196 @default.
• W4285089594 cites W2997304235 @default.
• W4285089594 cites W2999615587 @default.
• W4285089594 cites W3005086430 @default.
• W4285089594 cites W3010059221 @default.
• W4285089594 cites W3014660692 @default.
• W4285089594 cites W3036262830 @default.
• W4285089594 cites W3082166395 @default.
• W4285089594 cites W3083961251 @default.
• W4285089594 cites W3092147966 @default.
• W4285089594 cites W3096808766 @default.
• W4285089594 cites W3098095827 @default.
• W4285089594 cites W3107105751 @default.
• W4285089594 cites W3121588992 @default.
• W4285089594 cites W3122259034 @default.
• W4285089594 cites W3122628886 @default.
• W4285089594 cites W3123594767 @default.
• W4285089594 cites W3124669976 @default.
• W4285089594 cites W3125446544 @default.
• W4285089594 cites W3126032681 @default.
• W4285089594 cites W3155736180 @default.
• W4285089594 cites W3164940827 @default.
• W4285089594 cites W3165539072 @default.
• W4285089594 cites W3169238670 @default.
• W4285089594 cites W3200888467 @default.
• W4285089594 cites W3209809080 @default.
• W4285089594 cites W4205539948 @default.
• W4285089594 cites W4205810599 @default.
• W4285089594 doi "https://doi.org/10.1186/s40854-022-00366-1" @default.
• W4285089594 hasPublicationYear "2022" @default.
• W4285089594 type Work @default.
• W4285089594 citedByCount "5" @default.
• W4285089594 countsByYear W42850895942022 @default.
• W4285089594 countsByYear W42850895942023 @default.
• W4285089594 crossrefType "journal-article" @default.
• W4285089594 hasAuthorship W4285089594A5035662031 @default.
• W4285089594 hasAuthorship W4285089594A5061104415 @default.
• W4285089594 hasBestOaLocation W42850895941 @default.
• W4285089594 hasConcept C11413529 @default.
• W4285089594 hasConcept C119857082 @default.
• W4285089594 hasConcept C154945302 @default.
• W4285089594 hasConcept C162118730 @default.
• W4285089594 hasConcept C162324750 @default.
• W4285089594 hasConcept C175444787 @default.
• W4285089594 hasConcept C178350159 @default.
• W4285089594 hasConcept C181622380 @default.
• W4285089594 hasConcept C2780759654 @default.
• W4285089594 hasConcept C2864544 @default.
• W4285089594 hasConcept C41008148 @default.
• W4285089594 hasConceptScore W4285089594C11413529 @default.
• W4285089594 hasConceptScore W4285089594C119857082 @default.
• W4285089594 hasConceptScore W4285089594C154945302 @default.
• W4285089594 hasConceptScore W4285089594C162118730 @default.
• W4285089594 hasConceptScore W4285089594C162324750 @default.
• W4285089594 hasConceptScore W4285089594C175444787 @default.
• W4285089594 hasConceptScore W4285089594C178350159 @default.
• W4285089594 hasConceptScore W4285089594C181622380 @default.
• W4285089594 hasConceptScore W4285089594C2780759654 @default.
• W4285089594 hasConceptScore W4285089594C2864544 @default.
• W4285089594 hasConceptScore W4285089594C41008148 @default.
• W4285089594 hasIssue "1" @default.
• W4285089594 hasLocation W42850895941 @default.
• W4285089594 hasOpenAccess W4285089594 @default.
• W4285089594 hasPrimaryLocation W42850895941 @default.
• W4285089594 hasRelatedWork W118608213 @default.
• W4285089594 hasRelatedWork W1517605583 @default.
• W4285089594 hasRelatedWork W209931124 @default.
• W4285089594 hasRelatedWork W2182090269 @default.
• W4285089594 hasRelatedWork W2339492953 @default.
• W4285089594 hasRelatedWork W24614452 @default.

• next