IDEAS home Printed from https://ideas.repec.org/p/hal/journl/hal-03540319.html
   My bibliography  Save this paper

Designing labor market recommender systems: the importance of job seeker preferences and competition

Author

Listed:
  • Victor Alfonso Naya

    (LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique, TAU - TAckling the Underspecified - LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - Centre Inria de l'Université Paris-Saclay - Centre Inria de Saclay - Inria - Institut National de Recherche en Informatique et en Automatique)

  • Guillaume Bied

    (CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - GENES - Groupe des Écoles Nationales d'Économie et Statistique - X - École polytechnique - IP Paris - Institut Polytechnique de Paris - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - GENES - Groupe des Écoles Nationales d'Économie et Statistique - IP Paris - Institut Polytechnique de Paris - CNRS - Centre National de la Recherche Scientifique, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique, TAU - TAckling the Underspecified - LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - Centre Inria de l'Université Paris-Saclay - Centre Inria de Saclay - Inria - Institut National de Recherche en Informatique et en Automatique)

  • Philippe Caillou

    (LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique, TAU - TAckling the Underspecified - LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - Centre Inria de l'Université Paris-Saclay - Centre Inria de Saclay - Inria - Institut National de Recherche en Informatique et en Automatique)

  • Bruno Crépon

    (CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - GENES - Groupe des Écoles Nationales d'Économie et Statistique - X - École polytechnique - IP Paris - Institut Polytechnique de Paris - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - GENES - Groupe des Écoles Nationales d'Économie et Statistique - IP Paris - Institut Polytechnique de Paris - CNRS - Centre National de la Recherche Scientifique)

  • Christophe Gaillac

    (TSE-R - Toulouse School of Economics - UT Capitole - Université Toulouse Capitole - UT - Université de Toulouse - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement, CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - GENES - Groupe des Écoles Nationales d'Économie et Statistique - X - École polytechnique - IP Paris - Institut Polytechnique de Paris - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - GENES - Groupe des Écoles Nationales d'Économie et Statistique - IP Paris - Institut Polytechnique de Paris - CNRS - Centre National de la Recherche Scientifique)

  • Elia Pérennes

    (Pôle emploi (France), CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - GENES - Groupe des Écoles Nationales d'Économie et Statistique - X - École polytechnique - IP Paris - Institut Polytechnique de Paris - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - GENES - Groupe des Écoles Nationales d'Économie et Statistique - IP Paris - Institut Polytechnique de Paris - CNRS - Centre National de la Recherche Scientifique)

  • Michèle Sebag

    (CNRS - Centre National de la Recherche Scientifique, TAU - TAckling the Underspecified - LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique - Centre Inria de l'Université Paris-Saclay - Centre Inria de Saclay - Inria - Institut National de Recherche en Informatique et en Automatique, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique - Inria - Institut National de Recherche en Informatique et en Automatique - CentraleSupélec - Université Paris-Saclay - CNRS - Centre National de la Recherche Scientifique)

Abstract

We examine the properties of a recommender algorithm currently under construction at the Public Employment Service (PES) in France, before its implementation in the field. The algorithm associates to each offer-job seeker pair a predicted "matching probability" using a very large set of covariates. We first compare this new AI algorithm with a matching tool mimicking the one currently used at the PES, based on a score measuring the "proximity" between the job seeker's profile or preference and the characteristics of the offer. We detail and discuss the trade-off between matching probability and preference score when switching from one system to the other. We also examine the issue of congestion. We show on the one hand that the AI algorithm tends to increase congestion and on the other hand that this strongly reduces its performance. We finally show that the use of optimal transport to derive recommendations from the matching probability matrix allows to mitigate this problem significantly. The main lesson at this stage is that an algorithm ignoring preferences and competition in the labor market would have very limited performances but that tweaking the algorithm to fit these dimensions improves substantially its properties, at least "in the lab".

Suggested Citation

  • Victor Alfonso Naya & Guillaume Bied & Philippe Caillou & Bruno Crépon & Christophe Gaillac & Elia Pérennes & Michèle Sebag, 2021. "Designing labor market recommender systems: the importance of job seeker preferences and competition," Post-Print hal-03540319, HAL.
    • Handle: RePEc:hal:journl:hal-03540319
    Note: View the original document on HAL open archive server: https://inria.hal.science/hal-03540319v1
    as

    Download full text from publisher

    File URL: https://inria.hal.science/hal-03540319v1/document
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Kässi, Otto & Lehdonvirta, Vili, 2018. "Online labour index: Measuring the online gig economy for policy and research," Technological Forecasting and Social Change, Elsevier, vol. 137(C), pages 241-248.
    2. Michèle Belot & Philipp Kircher & Paul Muller, 2022. "How Wage Announcements Affect Job Search—A Field Experiment," American Economic Journal: Macroeconomics, American Economic Association, vol. 14(4), pages 1-67, October.
    3. Arnaud Dupuy & Alfred Galichon, 2014. "Personality Traits and the Marriage Market," Journal of Political Economy, University of Chicago Press, vol. 122(6), pages 1271-1319.
    4. Jenkins, Stephen P, 1995. "Easy Estimation Methods for Discrete-Time Duration Models," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 57(1), pages 129-138, February.
    5. Michèle Belot & Philipp Kircher & Paul Muller, 2019. "Providing Advice to Jobseekers at Low Cost: An Experimental Study on Online Advice," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 86(4), pages 1411-1447.
    6. Edward P. Lazear & Kathryn L. Shaw & Christopher T. Stanton, 2018. "Who Gets Hired? The Importance of Competition among Applicants," Journal of Labor Economics, University of Chicago Press, vol. 36(S1), pages 133-181.
    7. Alexandre Mas & Amanda Pallais, 2017. "Valuing Alternative Work Arrangements," American Economic Review, American Economic Association, vol. 107(12), pages 3722-3759, December.
    8. Alfred Galichon, 2016. "Optimal transport methods in economics," Post-Print hal-03256830, HAL.
    9. Randall Wright & Philipp Kircher & Benoit Julîen & Veronica Guerrieri, 2017. "Directed Search: A Guided Tour," NBER Working Papers 23884, National Bureau of Economic Research, Inc.
    10. Alfred Galichon, 2016. "Optimal Transport Methods in Economics," Economics Books, Princeton University Press, edition 1, number 10870.
    11. David H. Autor, 2001. "Wiring the Labor Market," Journal of Economic Perspectives, American Economic Association, vol. 15(1), pages 25-40, Winter.
    12. Hector Chade & Jan Eeckhout & Lones Smith, 2017. "Sorting through Search and Matching Models in Economics," Journal of Economic Literature, American Economic Association, vol. 55(2), pages 493-544, June.
    13. repec:spo:wpmain:info:hdl:2441/361levbcs399s9oa154em6h9jl is not listed on IDEAS
    14. Arnaud Dupuy & Alfred Galichon, 2014. "Personality traits and the marriage market," Post-Print hal-03470458, HAL.
    15. John J. Horton, 2017. "The Effects of Algorithmic Labor Market Recommendations: Evidence from a Field Experiment," Journal of Labor Economics, University of Chicago Press, vol. 35(2), pages 345-385.
    16. Pierre-André Chiappori & Bernard Salanié, 2016. "The Econometrics of Matching Models," Journal of Economic Literature, American Economic Association, vol. 54(3), pages 832-861, September.
    17. Danielle Li & Lindsey R. Raymond & Peter Bergman, 2020. "Hiring as Exploration," NBER Working Papers 27736, National Bureau of Economic Research, Inc.
    18. repec:hal:spmain:info:hdl:2441/361levbcs399s9oa154em6h9jl is not listed on IDEAS
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Carlier, Guillaume & Dupuy, Arnaud & Galichon, Alfred & Sun, Yifei, 2021. "SISTA: Learning Optimal Transport Costs under Sparsity Constraints," IZA Discussion Papers 14397, Institute of Labor Economics (IZA).
    2. Alfred Galichon & Bernard Salani'e, 2021. "Cupid's Invisible Hand: Social Surplus and Identification in Matching Models," Papers 2106.02371, arXiv.org, revised Jan 2023.
    3. Salanié, Bernard & Chiappori, Pierre-André, 2021. "Mating Markets," CEPR Discussion Papers 16041, C.E.P.R. Discussion Papers.
      • Pierre-André Chiappori & Bernard Salanié, 2021. "Mating Markets," Working Papers 2021-016, Human Capital and Economic Opportunity Working Group.
    4. Dupuy, Arnaud & Galichon, Alfred & Sun, Yifei, 2016. "Estimating Matching Affinity Matrix under Low-Rank Constraints," IZA Discussion Papers 10449, Institute of Labor Economics (IZA).
    5. Alfred Galichon & Bernard Salanié, 2023. "Structural Estimation of Matching Markets with Transferable Utility," Post-Print hal-03935865, HAL.
    6. Alfred Galichon & Bernard Salani'e, 2021. "Structural Estimation of Matching Markets with Transferable Utility," Papers 2109.07932, arXiv.org.
    7. Baiyu Dong & Yu-Wei Hsieh & Xing Zhang, 2022. "Implementing Maximum Likelihood Estimation of Empirical Matching Models," Computational Economics, Springer;Society for Computational Economics, vol. 59(1), pages 1-32, January.
    8. Adda, Jérôme & Pinotti, Paolo & Tura, Giulia, 2020. "There's More to Marriage than Love: The Effect of Legal Status and Cultural Distance on Intermarriages and Separations," CEPR Discussion Papers 14432, C.E.P.R. Discussion Papers.
    9. Michèle Belot & Philipp Kircher & Paul Muller, 2022. "How Wage Announcements Affect Job Search—A Field Experiment," American Economic Journal: Macroeconomics, American Economic Association, vol. 14(4), pages 1-67, October.
    10. Principi, Giulio & Wakker, Peter P. & Wang, Ruodu, 0. "Antimonotonicity for preference axioms: the natural counterpart to comonotonicity," Theoretical Economics, Econometric Society.
    11. Bisin, Alberto & Tura, Giulia, 2019. "Marriage, Fertility, and Cultural Integration in Italy," CEPR Discussion Papers 14179, C.E.P.R. Discussion Papers.
    12. Gomez-Herrera, Estrella & Mueller-Langer, Frank, 2024. "Does information disclosure affect the gender gap in bidding behavior? Empirical evidence from a natural experiment on a large online labor platform," Labour Economics, Elsevier, vol. 90(C).
    13. Ni Huang & Gordon Burtch & Yili Hong & Paul A. Pavlou, 2020. "Unemployment and Worker Participation in the Gig Economy: Evidence from an Online Labor Market," Information Systems Research, INFORMS, vol. 31(2), pages 431-448, June.
    14. Kuan‐Ming Chen & Yu‐Wei Hsieh & Ming‐Jen Lin, 2023. "Reducing Recommendation Inequality Via Two‐Sided Matching: A Field Experiment Of Online Dating," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 64(3), pages 1201-1221, August.
    15. Job Boerma & Aleh Tsyvinski & Alexander P. Zimin, 2022. "Bunching and Taxing Multidimensional Skills," Papers 2204.13481, arXiv.org, revised Apr 2025.
    16. Itai Ashlagi & Mark Braverman & Yash Kanoria & Peng Shi, 2020. "Clearing Matching Markets Efficiently: Informative Signals and Match Recommendations," Management Science, INFORMS, vol. 66(5), pages 2163-2193, May.
    17. Kuhn, Peter & Shen, Kailing & Zhang, Shuo, 2020. "Gender-targeted job ads in the recruitment process: Facts from a Chinese job board," Journal of Development Economics, Elsevier, vol. 147(C).
    18. Qinyou Hu, 2024. "Social status and marriage markets: Evaluating a Hukou policy in China," Review of Economics of the Household, Springer, vol. 22(2), pages 477-509, June.
    19. Pierre-André Chiappori & Carlo Fiorio & Alfred Galichon & Stefano Verzillo, 2022. "Assortative Matching on Income," Working Papers 2022-006, Human Capital and Economic Opportunity Working Group.
    20. Alberto Bisin & Giulia Tura, 2019. "Marriage, Fertility, and Cultural Integration of Immigrants in Italy," Working Papers 2019-063, Human Capital and Economic Opportunity Working Group.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hal:journl:hal-03540319. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.