Equally accurate models flag different people for the same review budget

Risk models routinely rank individuals to fill fixed human-review budgets in advising, human resources, and credit underwriting, yet choosing among equally accurate models is rarely treated as consequential. We audit predictive and explanation multiplicity across five tabular benchmarks—employee attrition, higher-education student dropout, census income, consumer credit, and a redundant-signal synthetic task—over 30 repeated stratified splits. Within each split, every model within 0.02 validation AUC of the optimum fills the identical top-k review capacity. Near-optimal models differ by only 0.013–0.035 in test AUC and 1.1–6.7 percentage points in event capture, yet 44%–75% of individuals flagged at a 10% budget are omitted by competing near-optimal models. Conflict concentrates tightly in Quintile 1 around the capacity cut-off and persists inside explanations: unanimously flagged cases at a 20% budget trigger conflicting top occlusion reasons in 13%–84% of cases and divergent routing in 0%–34%. Selective consensus gating lowers routing instability by 29%–79%, primarily by withholding borderline cut-off cases and shrinking queue coverage. Under review constraints, selecting among equally accurate models is an allocative governance choice rather than a neutral technicality.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24304612
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Equally accurate models flag different people for the same review budget

Kang Liu
3 links
Zenodo (CERN European Organization for Nuclear Research)
Explainable Artificial Intelligence (XAI)
preprint

Equally accurate models flag different people for the same review budget

Kang Liu
preprint en

Abstract

Risk models routinely rank individuals to fill fixed human-review budgets in advising, human resources, and credit underwriting, yet choosing among equally accurate models is rarely treated as consequential. We audit predictive and explanation multiplicity across five tabular benchmarks—employee attrition, higher-education student dropout, census income, consumer credit, and a redundant-signal synthetic task—over 30 repeated stratified splits. Within each split, every model within 0.02 validation AUC of the optimum fills the identical top-k review capacity. Near-optimal models differ by only 0.013–0.035 in test AUC and 1.1–6.7 percentage points in event capture, yet 44%–75% of individuals flagged at a 10% budget are omitted by competing near-optimal models. Conflict concentrates tightly in Quintile 1 around the capacity cut-off and persists inside explanations: unanimously flagged cases at a 20% budget trigger conflicting top occlusion reasons in 13%–84% of cases and divergent routing in 0%–34%. Selective consensus gating lowers routing instability by 29%–79%, primarily by withholding borderline cut-off cases and shrinking queue coverage. Under review constraints, selecting among equally accurate models is an allocative governance choice rather than a neutral technicality.

Zenodo (CERN European Organization for Nuclear Research)
Shandong Normal University (CN)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon