A Job I Like or a Job I Can Get: Designing Job Recommender Systems Using Field Experiments

2026-03-23

AI Summary

This study addresses a critical gap in existing job recommendation systems, which predominantly optimize for behavioral metrics such as clicks, applications, or hires while neglecting actual applicant welfare. For the first time, we integrate applicant welfare into the recommendation framework by formulating a structured job-seeking model that jointly considers utility and application success probability. We identify a “reversal problem” between observed behavioral data and welfare-oriented objectives and propose a welfare-optimal ranking strategy based on the Expected Surplus Index. Through a randomized field experiment on a real-world employment platform—combining causal inference with algorithmic optimization—we demonstrate that our approach significantly outperforms baseline methods relying solely on historical behavior or single-dimensional signals, closely approaching the theoretical welfare optimum and yielding substantial real-world welfare gains.

Technology Category

Search and Optimization: Algorithm ConfigurationMachine Learning: Learning Preferences or RankingsData Mining & Knowledge Management: Recommender Systems

Application Category

User Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingResponsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Recommendation systems (RSs) are increasingly used to guide job seekers on online platforms, yet the algorithms currently deployed are typically optimized for predictive objectives such as clicks, applications, or hires, rather than job seekers' welfare. We develop a job-search model with an application stage in which the value of a vacancy depends on two dimensions: the utility it delivers to the worker and the probability that an application succeeds. The model implies that welfare-optimal RSs rank vacancies by an expected-surplus index combining both, and shows why rankings based solely on utility, hiring probabilities, or observed application behavior are generically suboptimal, an instance of the inversion problem between behavior and welfare. We test these predictions and quantify their practical importance through two randomized field experiments conducted with the French public employment service. The first experiment, comparing existing algorithms and their combinations, provides behavioral evidence that both dimensions shape application decisions. Guided by the model and these results, the second experiment extends the comparison to an RS designed to approximate the welfare-optimal ranking. The experiments generate exogenous variation in the vacancies shown to job seekers, allowing us to estimate the model, validate its behavioral predictions, and construct a welfare metric. Algorithms informed by the model-implied optimal ranking substantially outperform existing approaches and perform close to the welfare-optimal benchmark. Our results show that embedding predictive tools within a simple job-search framework and combining it with experimental evidence yields recommendation rules with substantial welfare gains in practice.

Problem

• job recommender systems
• welfare optimization
• hiring probability
• job search
• inversion problem

Innovation

• welfare-optimal recommendation
• job recommender systems
• field experiments
• expected-surplus index
• inversion problem