Metraipolis › archive › dc_7412e20857ec

Beyond Aggregate Calibration: Decomposing Income-Conditional Recall Disparities in Automated Credit Default Prediction — arXiv:2608.08202

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08202
License (as archived)
CC0-1.0
Archived
2026-10-19T08:55:08.254Z
SHA-256 of the archived text
386347329639e5d1662d1574b721e6afb3613951972a2ab1440b22a4fcebbace
Stable URL of this page
https://metraipolis.com/documento/dc_7412e20857ec

How to cite

Beyond Aggregate Calibration: Decomposing Income-Conditional Recall Disparities in Automated Credit Default Prediction — arXiv:2608.08202 — arXiv (en), https://arxiv.org/abs/2608.08202 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7412e20857ec (Metraipolis archive dc_7412e20857ec, sha256 386347329639e5d1662d1574b721e6afb3613951972a2ab1440b22a4fcebbace)
BibTeX
@misc{dc7412e20857ec,
  title = {Beyond Aggregate Calibration: Decomposing Income-Conditional Recall Disparities in Automated Credit Default Prediction — arXiv:2608.08202},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08202},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7412e20857ec; sha256 386347329639e5d1662d1574b721e6afb3613951972a2ab1440b22a4fcebbace},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08202. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data-centric curation pipelines frequently rely on model confidence scores to flag and filter noisy or mislabeled training instances. Evaluating this filtering convention on a large-scale consumer lending sample (LendingClub, N = 1,344,936) uncovers an underlying demographic asymmetry: high-income defaulters are disproportionately classified as label noise relative to low-income defaulters (Cramer's V approximately 0.03-0.07). Re-examining this behavior through the lens of equal opportunity [Hardt et al., 2016] reveals a far more severe discrepancy: a 16.86 percentage point gap in true positive rate (recall) between high- and low-income borrowers who ultimately defaulted. Implementing a sequential feature-blinding methodology allows us to isolate the drivers of this disparity across three distinct mechanisms: (1) direct reliance on self-reported applicant income; (2) algorithmic absorption of upstream institutional bias encoded within origination interest rates; and (3) a residual disparity (3.55 percentage points in cross-validation; 2.56 percentage points on a held-out test partition, Z = -4.04, p < 0.0001) that remains even after purging both income and interest rates from the model. Out-of-sample signed SHAP valuations demonstrate that this residual gap is maintained by structural proxies, most notably loan amount and home ownership status. These empirical findings show that simply blinding an algorithm to sensitive attributes fails to ensure fairness when institutional pricing decisions and behavioral proxy variables collectively reconstruct the omitted signals. We outline the practical implications of these findings for auditing data-centric AI workflows within regulated financial institutions.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CY).
Categorie arXiv: Machine Learning (cs.LG) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.08202 — 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 2026-10-19T08:51:53.766Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).