---
id: "lib-2026-10-31-learning-about-markets-from-models-evidence-from"
type: "library"
title: "Learning about Markets from Models: Evidence from an AI Hiring Platform"
lang: "EN"
org: "Harvard Business School"
source_type: "Other"
date: "2026-10-31"
week: "2026-W45"
url: "https://nosov.ai/library/lib-2026-10-31-learning-about-markets-from-models-evidence-from/"
original_url: "https://arxiv.org/abs/2611.01226"
tier: "A"
tier_name: "Strong evidence"
tier_reason: "Harvard Business School economists (Alidaee, Khanna, Koning) analyse 172,242 applications and firm-specific retention models on a Mexican hiring platform with stated estimators, confidence intervals and recalibration checks."
summary_basis: "full-text"
original_minutes: "70"
tags: ["future of work", "hiring", "hr"]
---

# Learning about Markets from Models: Evidence from an AI Hiring Platform

Tier A (Strong evidence): Harvard Business School economists (Alidaee, Khanna, Koning) analyse 172,242 applications and firm-specific retention models on a Mexican hiring platform with stated estimators, confidence intervals and recalibration checks.

Summary based on the full text.

## In short

A paper (arXiv, 31 October 2026) by Hossein Alidaee, Tarun Khanna and Rembrand Koning of HBS. A hiring platform for large employers of low-skill workers in Mexico trains one model per firm to predict 90-day retention from a common psychometric test. Each model predicts well at its own firm and no better than chance at others. Comparing the models across firms still yields information: which applicants would stay longer elsewhere, and how differently firms value the same traits.

## Key numbers

- 172,242: job applications from three of the platform's largest clients, 2020-2025
- 0.855 to 0.914: AUC of each firm's own retention model at its own firm
- 26.9 vs 16.4 percentage points: predicted retention gain from redirecting an application to its best-fit firm, top vs bottom trait quintile
- 21.8 to 15.1 percentage points: mean gain after equalising baseline retention across firms

## What it reports

- Firm models rank a stayer above a leaver at least 85% of the time at their own firm (random-forest AUCs 0.855, 0.891, 0.914), but are essentially useless at other firms.
- Scoring every application with every firm's model gives a firm-application matrix. Top-quintile applications gain 26.9 points of predicted retention from redirection, bottom-quintile 16.4.
- Recalibrating models to the same average retention removes gains due only to higher baseline retention: the top quintile loses 7 points of gain, the bottom 2.2.
- Mean redirection gap falls from 21.8 to 15.1 points after baseline equalisation.
- Firms disagree on whether important traits raise or lower retention at the margin, even in this low-skill market.
- The authors call this a "model comparison externality": value from a platform holding many firm models even when pooling data does not improve any one prediction.

## How they got it

Platform data on assessments and tenure, firm-specific random forests chosen by nested cross-validation, cross-firm scoring, and a share-matching inversion borrowed from discrete-choice demand estimation to separate worker-firm complementarity from sorting on baseline retention.

## Limits

- Three firms, one country, one psychometric instrument, one outcome (90-day tenure).
- Redirection gains are model predictions, not observed outcomes of reassigned workers.
- Applicants are people who passed each firm's existing hiring process, which limits what the models see.

## Why it matters for companies

A retention or screening model trained on your own hires does not transfer to another employer, and a vendor's pooled model may not transfer to you. The comparison across firms is where the market insight sits: which traits competitors reward and where your hiring differs. Firms using such platforms should ask what cross-client comparisons the vendor runs and who gets the results.

Original: https://arxiv.org/abs/2611.01226