Guillaume Bied, Philippe Caillou, Bruno Crépon, Christophe Gaillac, Elia Pérennes, Michèle Sebag
arXiv 23 Mar 2026 · Econometrics
arXiv:2603.21699 · PDF · OpenAlex · Extracted main text
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.
appendix boundary found by appendix_command · 64% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Altmann, Steffen and Glenny, Anita M and Mahlstedt, Robert and Sebal… (2022) The Direct and Indirect Effects of Online Job Search Advice | 1.000 | 6 | 3 | 100% |
| 2 | Hensvik, Lena and Le Barbanchon, Thomas and Rathelot, Roland (2022) How can AI improve search and matching? Evidence from 59 million personalized job recommendations | 1.000 | 6 | 3 | 100% |
| 3 | Behaghel, Luc and Dromundo, Sofia and Gurgand, Marc and Hazard, Yaga… (2024) The Potential of Recommender Systems for Directing Job Search: A Large-Scale Experiment | 1.000 | 5 | 3 | 100% |
| 4 | Bied, Guillaume and Perennes, Elia and Naya, Victor Alfonso and Cail… (2021) Congestion-avoiding job recommendation with optimal transport self | 0.928 | 4 | 3 | 100% |
| 5 | Bächli, Mirjam and Lalive, Rafael and Pellizzari, Michele (2025) Helping jobseekers with recommendations based on skill profiles or past experience: Evidence from a randomized intervention | 0.874 | 5 | 2 | 100% |
| 6 | Belot, Michèle and de Koning, Bart and Fouarge, Didier and Kircher,… (2025) Advising Job Seekers in Occupations with Poor Prospects: A Field Experiment | 0.874 | 5 | 2 | 100% |
| 7 | Belot, Michele and Kircher, Philipp and Muller, Paul (2019) Providing advice to jobseekers at low cost: An experimental study on online advice | 0.811 | 4 | 2 | 100% |
| 8 | Chernozhukov, Victor and Demirer, Mert and Duflo, Esther and Fernand… (2018) Generic machine learning inference on heterogenous treatment effects in randomized experiments | 0.737 | 4 | 3 | 50% |
| 9 | Algan, Yann and Crépon, Bruno and Glover, Dylan (2020) Are active labor market policies directed at firms effective? Evidence from a randomized evaluation with local employment agencies | 0.737 | 3 | 2 | 100% |
| 10 | Su, Yi and Bayoumi, Magd and Joachims, Thorsten (2022) Optimizing Rankings for Recommendation in Matching Markets | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 43 scored citations.