Saved in:
Bibliographic Details
Main Authors: Dong, Evan, Garg, Nikhil, Dean, Sarah
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11513
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915735903666176
author Dong, Evan
Garg, Nikhil
Dean, Sarah
author_facet Dong, Evan
Garg, Nikhil
Dean, Sarah
contents Machine learning models are often used to make predictions about admissions process outcomes, such as for colleges or jobs. However, such decision processes differ substantially from the conventional machine learning paradigm. Because admissions decisions are capacity-constrained, whether a student is admitted depends on the other applicants who apply. We show how this dependence affects predictive performance even in otherwise ideal settings. Theoretically, we introduce two concepts that characterize the relationship between admission function properties, machine learning representation, and generalization to applicant pool distribution shifts: instability, which measures how many existing decisions can change when a single new applicant is introduced; and variability, which measures the number of unique students whose decisions can change. Empirically, we illustrate our theory on individual-level admissions data from the New York City high school matching system, showing that machine learning performance degrades as the applicant pool increasingly differs from the training data. Furthermore, there are larger performance drops for schools using decision rules that are more unstable and variable. Our work raises questions about the reliability of predicting individual admissions probabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Capacity Constraints Make Admissions Processes Less Predictable
Dong, Evan
Garg, Nikhil
Dean, Sarah
Computers and Society
K.4.0
Machine learning models are often used to make predictions about admissions process outcomes, such as for colleges or jobs. However, such decision processes differ substantially from the conventional machine learning paradigm. Because admissions decisions are capacity-constrained, whether a student is admitted depends on the other applicants who apply. We show how this dependence affects predictive performance even in otherwise ideal settings. Theoretically, we introduce two concepts that characterize the relationship between admission function properties, machine learning representation, and generalization to applicant pool distribution shifts: instability, which measures how many existing decisions can change when a single new applicant is introduced; and variability, which measures the number of unique students whose decisions can change. Empirically, we illustrate our theory on individual-level admissions data from the New York City high school matching system, showing that machine learning performance degrades as the applicant pool increasingly differs from the training data. Furthermore, there are larger performance drops for schools using decision rules that are more unstable and variable. Our work raises questions about the reliability of predicting individual admissions probabilities.
title Capacity Constraints Make Admissions Processes Less Predictable
topic Computers and Society
K.4.0
url https://arxiv.org/abs/2601.11513