Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207673048> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3207673048 abstract "The special and important problems of default prediction for municipal bonds are addressed using a combination of text embeddings from a pre-trained transformer network, a fully connected neural network, and synthetic oversampling. The combination of these techniques provides significant improvement in performance over human estimates, linear models, and boosted ensemble models, on data with extreme imbalance. Less than 0.2% of municipal bonds default, but our technique predicts 9 out of 10 defaults at the time of issue, without using bond ratings, at a cost of false positives on less than 0.1% non-defaulting bonds. The results hold the promise of reducing the cost of capital for local public goods, which are vital for society, and bring techniques previously used in personal credit and public equities (or national fixed income), as well as the current generation of embedding techniques, to sub-sovereign credit decisions." @default.
- W3207673048 created "2021-10-25" @default.
- W3207673048 creator A5006371830 @default.
- W3207673048 date "2021-10-13" @default.
- W3207673048 modified "2023-09-27" @default.
- W3207673048 title "Bond Default Prediction with Text Embeddings, Undersampling and Deep Learning." @default.
- W3207673048 cites W2021073784 @default.
- W3207673048 cites W2025769637 @default.
- W3207673048 cites W2148143831 @default.
- W3207673048 cites W2891299486 @default.
- W3207673048 cites W2962862931 @default.
- W3207673048 cites W2970641574 @default.
- W3207673048 cites W3010059221 @default.
- W3207673048 cites W3028931246 @default.
- W3207673048 cites W3037419396 @default.
- W3207673048 cites W3047063927 @default.
- W3207673048 cites W3095606640 @default.
- W3207673048 cites W3111356309 @default.
- W3207673048 cites W3124141057 @default.
- W3207673048 cites W3124398128 @default.
- W3207673048 cites W3135156596 @default.
- W3207673048 hasPublicationYear "2021" @default.
- W3207673048 type Work @default.
- W3207673048 sameAs 3207673048 @default.
- W3207673048 citedByCount "0" @default.
- W3207673048 crossrefType "posted-content" @default.
- W3207673048 hasAuthorship W3207673048A5006371830 @default.
- W3207673048 hasConcept C10138342 @default.
- W3207673048 hasConcept C101738243 @default.
- W3207673048 hasConcept C119857082 @default.
- W3207673048 hasConcept C136536468 @default.
- W3207673048 hasConcept C149782125 @default.
- W3207673048 hasConcept C154945302 @default.
- W3207673048 hasConcept C162118730 @default.
- W3207673048 hasConcept C162324750 @default.
- W3207673048 hasConcept C178350159 @default.
- W3207673048 hasConcept C197323446 @default.
- W3207673048 hasConcept C2776257435 @default.
- W3207673048 hasConcept C31258907 @default.
- W3207673048 hasConcept C41008148 @default.
- W3207673048 hasConcept C44309892 @default.
- W3207673048 hasConcept C50644808 @default.
- W3207673048 hasConcept C69637215 @default.
- W3207673048 hasConcept C69738904 @default.
- W3207673048 hasConceptScore W3207673048C10138342 @default.
- W3207673048 hasConceptScore W3207673048C101738243 @default.
- W3207673048 hasConceptScore W3207673048C119857082 @default.
- W3207673048 hasConceptScore W3207673048C136536468 @default.
- W3207673048 hasConceptScore W3207673048C149782125 @default.
- W3207673048 hasConceptScore W3207673048C154945302 @default.
- W3207673048 hasConceptScore W3207673048C162118730 @default.
- W3207673048 hasConceptScore W3207673048C162324750 @default.
- W3207673048 hasConceptScore W3207673048C178350159 @default.
- W3207673048 hasConceptScore W3207673048C197323446 @default.
- W3207673048 hasConceptScore W3207673048C2776257435 @default.
- W3207673048 hasConceptScore W3207673048C31258907 @default.
- W3207673048 hasConceptScore W3207673048C41008148 @default.
- W3207673048 hasConceptScore W3207673048C44309892 @default.
- W3207673048 hasConceptScore W3207673048C50644808 @default.
- W3207673048 hasConceptScore W3207673048C69637215 @default.
- W3207673048 hasConceptScore W3207673048C69738904 @default.
- W3207673048 hasLocation W32076730481 @default.
- W3207673048 hasOpenAccess W3207673048 @default.
- W3207673048 hasPrimaryLocation W32076730481 @default.
- W3207673048 hasRelatedWork W1529576516 @default.
- W3207673048 hasRelatedWork W1594780990 @default.
- W3207673048 hasRelatedWork W1848525158 @default.
- W3207673048 hasRelatedWork W1941828766 @default.
- W3207673048 hasRelatedWork W197546077 @default.
- W3207673048 hasRelatedWork W2014506576 @default.
- W3207673048 hasRelatedWork W2029666602 @default.
- W3207673048 hasRelatedWork W2088005313 @default.
- W3207673048 hasRelatedWork W2088615280 @default.
- W3207673048 hasRelatedWork W2103336046 @default.
- W3207673048 hasRelatedWork W2169384819 @default.
- W3207673048 hasRelatedWork W2185016091 @default.
- W3207673048 hasRelatedWork W2264602268 @default.
- W3207673048 hasRelatedWork W3122082718 @default.
- W3207673048 hasRelatedWork W3123686916 @default.
- W3207673048 hasRelatedWork W3124741642 @default.
- W3207673048 hasRelatedWork W3125026887 @default.
- W3207673048 hasRelatedWork W3149821286 @default.
- W3207673048 hasRelatedWork W90301210 @default.
- W3207673048 hasRelatedWork W1607379131 @default.
- W3207673048 isParatext "false" @default.
- W3207673048 isRetracted "false" @default.
- W3207673048 magId "3207673048" @default.
- W3207673048 workType "article" @default.