FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380048310> ?p ?o ?g. }

• W4380048310 abstract "Machine learning models have been used extensively for credit scoring, but the architectures employed suffer from a significant loss in accuracy out-of-sample and out-of-time. Further, the most common architectures do not effectively integrate economic scenarios to enable stress testing, cash flow, or yield estimation. The present research demonstrates that providing lifecycle and environment functions from Age-Period-Cohort analysis can significantly improve out-of-sample and out-of-time performance as well as enabling the model's use in both scoring and stress testing applications. This method is demonstrated for behavior scoring where account delinquency is one of the provided inputs, because behavior scoring has historically presented the most difficulties for combining credit scoring and stress testing. Our method works well in both origination and behavior scoring. The results are also compared to multihorizon survival models, which share the same architectural design with Age-Period-Cohort inputs and coefficients that vary with forecast horizon, but using a logistic regression estimation of the model. The analysis was performed on 30-year prime conforming US mortgage data. Nonlinear problems involving large amounts of alternate data are best at highlighting the advantages of machine learning. Data from Fannie Mae and Freddie Mac is not such a test case, but it serves the purpose of comparing these methods with and without Age-Period-Cohort inputs. In order to make a fair comparison, all models are given a panel structure where each account is observed monthly to determine default or non-default." @default.
• W4380048310 created "2023-06-10" @default.
• W4380048310 creator A5009361680 @default.
• W4380048310 creator A5031699638 @default.
• W4380048310 date "2023-06-08" @default.
• W4380048310 modified "2023-09-28" @default.
• W4380048310 title "Stabilizing machine learning models with Age-Period-Cohort inputs for scoring and stress testing" @default.
• W4380048310 cites W1496023527 @default.
• W4380048310 cites W1497131193 @default.
• W4380048310 cites W1570622790 @default.
• W4380048310 cites W1678356000 @default.
• W4380048310 cites W1836663529 @default.
• W4380048310 cites W1964611184 @default.
• W4380048310 cites W1977009091 @default.
• W4380048310 cites W1979638902 @default.
• W4380048310 cites W1990113270 @default.
• W4380048310 cites W1992978513 @default.
• W4380048310 cites W1993626219 @default.
• W4380048310 cites W1996039750 @default.
• W4380048310 cites W2005510983 @default.
• W4380048310 cites W2026706435 @default.
• W4380048310 cites W2032648409 @default.
• W4380048310 cites W2035908274 @default.
• W4380048310 cites W2036547589 @default.
• W4380048310 cites W2036753645 @default.
• W4380048310 cites W2041844120 @default.
• W4380048310 cites W2053891585 @default.
• W4380048310 cites W2064178952 @default.
• W4380048310 cites W2066927337 @default.
• W4380048310 cites W2070493638 @default.
• W4380048310 cites W2075159929 @default.
• W4380048310 cites W2103780778 @default.
• W4380048310 cites W2108673310 @default.
• W4380048310 cites W2113242816 @default.
• W4380048310 cites W2114717670 @default.
• W4380048310 cites W2118565421 @default.
• W4380048310 cites W2123260886 @default.
• W4380048310 cites W2125527920 @default.
• W4380048310 cites W2137029138 @default.
• W4380048310 cites W2148143831 @default.
• W4380048310 cites W2156901977 @default.
• W4380048310 cites W2165063012 @default.
• W4380048310 cites W2168020168 @default.
• W4380048310 cites W2217007515 @default.
• W4380048310 cites W2257712577 @default.
• W4380048310 cites W2496846218 @default.
• W4380048310 cites W2748025215 @default.
• W4380048310 cites W2753919178 @default.
• W4380048310 cites W2767338602 @default.
• W4380048310 cites W2895269073 @default.
• W4380048310 cites W2900798292 @default.
• W4380048310 cites W2942764569 @default.
• W4380048310 cites W2963232127 @default.
• W4380048310 cites W3009763662 @default.
• W4380048310 cites W3015337523 @default.
• W4380048310 cites W3034563984 @default.
• W4380048310 cites W3044323082 @default.
• W4380048310 cites W3048210715 @default.
• W4380048310 cites W3099478002 @default.
• W4380048310 cites W3102476541 @default.
• W4380048310 cites W3123936692 @default.
• W4380048310 cites W3124042673 @default.
• W4380048310 cites W3201090655 @default.
• W4380048310 cites W4200515018 @default.
• W4380048310 cites W4236137412 @default.
• W4380048310 cites W4242746271 @default.
• W4380048310 cites W4246259708 @default.
• W4380048310 cites W4246945034 @default.
• W4380048310 cites W4248611486 @default.
• W4380048310 cites W4296371202 @default.
• W4380048310 cites W4306956827 @default.
• W4380048310 cites W47998726 @default.
• W4380048310 doi "https://doi.org/10.3389/fams.2023.1195810" @default.
• W4380048310 hasPublicationYear "2023" @default.
• W4380048310 type Work @default.
• W4380048310 citedByCount "0" @default.
• W4380048310 crossrefType "journal-article" @default.
• W4380048310 hasAuthorship W4380048310A5009361680 @default.
• W4380048310 hasAuthorship W4380048310A5031699638 @default.
• W4380048310 hasBestOaLocation W43800483101 @default.
• W4380048310 hasConcept C10138342 @default.
• W4380048310 hasConcept C105795698 @default.
• W4380048310 hasConcept C119857082 @default.
• W4380048310 hasConcept C149782125 @default.
• W4380048310 hasConcept C151956035 @default.
• W4380048310 hasConcept C154945302 @default.
• W4380048310 hasConcept C162324750 @default.
• W4380048310 hasConcept C185592680 @default.
• W4380048310 hasConcept C198531522 @default.
• W4380048310 hasConcept C199360897 @default.
• W4380048310 hasConcept C2779201015 @default.
• W4380048310 hasConcept C33923547 @default.
• W4380048310 hasConcept C41008148 @default.
• W4380048310 hasConcept C43617362 @default.
• W4380048310 hasConcept C72563966 @default.
• W4380048310 hasConcept C7515471 @default.
• W4380048310 hasConceptScore W4380048310C10138342 @default.
• W4380048310 hasConceptScore W4380048310C105795698 @default.
• W4380048310 hasConceptScore W4380048310C119857082 @default.
• W4380048310 hasConceptScore W4380048310C149782125 @default.

• next