← 研踪 PaperTrailarXiv:2605.07979 · v2
The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
首次提交 2026-05-09 00:38
版本更新 2026-11-12 11:33
雷达观测 2026-11-13 14:16
摘要
The rise of machine learning has shifted targeted resource allocation in policy and humanitarian settings toward algorithmic targeting based on predicted risk scores. This approach is typically cheaper and faster than traditional screening procedures that directly observe the latent vulnerability status through physical verification. Yet, even access to the true conditional vulnerability probability cannot eliminate misallocation: aleatoric uncertainty over individual vulnerability status is irreducible, and probabilistic targeting inevitably misallocates some resources. In this work, we study how screening and algorithmic targeting should be optimally combined in a two-stage allocation framework, in which a screening stage observes true outcomes for a subset of units before a final allocation stage assigns the resource under a fixed coverage budget. We show that the optimal strategy screens units at the margin of algorithmic allocation, while directly targeting the highest-risk units. We empirically characterize when screening and algorithmic targeting act as complements or substitutes: efficiency gains from screening grow as the aleatoric uncertainty in the population increases. Finally, we characterize the relative value of screening and direct allocation, which yields a simple rule for splitting a program budget between the two: the optimal cutoff depends only on their cost ratio. We illustrate our framework with applications in income-based social protection programs and humanitarian demining in Colombia, where the tension between screening costs and allocation efficiency is operationally consequential
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-12 11:33 · 最新观测版本
The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
The rise of machine learning has shifted targeted resource allocation in policy and humanitarian settings toward algorithmic targeting based on predicted risk scores. This approach is typically cheaper and faster than traditional screening procedures that directly observe the latent vulnerability status through physical verification. Yet, even access to the true conditional vulnerability probability cannot eliminate misallocation: aleatoric uncertainty over individual vulnerability status is irreducible, and probabilistic targeting inevitably misallocates some resources. In this work, we study how screening and algorithmic targeting should be optimally combined in a two-stage allocation framework, in which a screening stage observes true outcomes for a subset of units before a final allocation stage assigns the resource under a fixed coverage budget. We show that the optimal strategy screens units at the margin of algorithmic allocation, while directly targeting the highest-risk units. We empirically characterize when screening and algorithmic targeting act as complements or substitutes: efficiency gains from screening grow as the aleatoric uncertainty in the population increases. Finally, we characterize the relative value of screening and direct allocation, which yields a simple rule for splitting a program budget between the two: the optimal cutoff depends only on their cost ratio. We illustrate our framework with applications in income-based social protection programs and humanitarian demining in Colombia, where the tension between screening costs and allocation efficiency is operationally consequential
查看此版本解读 →查看此版本原文 ↗