Metraipolis › archive › dc_8750ee5ab8d7
Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning — arXiv:2610.08869
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08869
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:35.731Z
- SHA-256 of the archived text
6b33b814204ff7832e5e4ad63d635c1219e526c62e1b080cbeabb8b5016d4f85- Stable URL of this page
https://metraipolis.com/documento/dc_8750ee5ab8d7
How to cite
Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning — arXiv:2610.08869 — arXiv (en), https://arxiv.org/abs/2610.08869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8750ee5ab8d7 (Metraipolis archive dc_8750ee5ab8d7, sha256 6b33b814204ff7832e5e4ad63d635c1219e526c62e1b080cbeabb8b5016d4f85)
BibTeX
@misc{dc8750ee5ab8d7,
title = {Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning — arXiv:2610.08869},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08869},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8750ee5ab8d7; sha256 6b33b814204ff7832e5e4ad63d635c1219e526c62e1b080cbeabb8b5016d4f85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Regulated credit scoring requires scores monotone non-decreasing in every exposure input. Deployed pipelines -- hand-crafted monotone aggregates feeding sign-constrained gradient boosting -- already meet this by composition; the open question is what learned temporal aggregation is worth inside one. We answer on five production-scale credit datasets at matched admissibility (one priced baseline convention excepted), with a monotone recurrent architecture whose per-input guarantee we extend, with proofs, to vector-valued inputs and to exogenously macro-conditioned decay gates, severities, thresholds, and peak memory. Two findings result. First, a strictness ladder: the value of learned monotone features rises with governance-frame strictness -- zero on unconstrained engineered panels, maximal in summaries-only frames -- replicated across two datasets and an official temporal-stability metric, though unconditioned features degrade on externally adjudicated later weeks. Second, a conditioning-delivery asymmetry under regime shift. On a train-on-boom, test-on-crisis mortgage design, two public macroeconomic series hurt as input columns, yet conditioning the recurrence on them delivers the paper's only learned-block crisis-cohort uplifts. The confirmed effect: +0.006 to +0.013 AUC on an internally pre-registered Freddie Mac replication, at all five held-out seeds. The discovery estimate: +0.015 to +0.021 on Fannie Mae (three of five seeds post hoc), worth 10-27 basis points of defaulted balance at an 80% approval cutoff, and grows with early-prepaid loans excluded. A state-level test identifies the mechanism: between-cohort calibration transfer. A pandemic-band episode bounds scope: under forbearance-distorted labels the gain generalizes at a quarter to a third of crisis size on Fannie Mae, on Freddie Mac only against the capacity control. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Risk Management (q-fin.RM) ; Machine Learning (cs.LG); Applications (stat.AP). Pagina del lavoro: https://arxiv.org/abs/2610.08869 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:14:15.361Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).