From rules to forests: rule-based versus statistical models for jobseeker profiling

Álvaro F. Junquera and Christoph Kern
Additional contact information
Álvaro F. Junquera: Centre d’Estudis Sociològics Sobre la Vida Quotidiana i el Treball, Institut d’Estudis del Treball, Universitat Autònoma de Barcelona, Bellaterra, Spain
Christoph Kern: University of Mannheim, Mannheim, Germany ; University of Maryland, College Park, USA ; Munich Center for Machine Learning (MCML), LMU Munich, Munich, Germany

Journal for Labour Market Research, 2025, vol. 59, Article 26

Abstract: "Public employment services (PES) commonly apply profiling models to target labor market programs to jobseekers at risk of becoming long-term unemployed. Such allocation systems often codify institutional experiences in a set of profiling rules, whose predictive ability, however, is seldomly tested. We systematically compare the predictive performance of a rule-based profiling procedure currently used by the PES in Catalonia, Spain, with the performance of statistical models in predicting future long-term unemployment (LTU) spells. Using comprehensive administrative data, we develop logit and machine learning models and evaluate their performance with respect to both model discrimination and calibration. Compared to the rule-based model used in Catalonia, our machine learning models achieve greater discrimination ability and remarkable improvements in calibration. Particularly, our random forest model is able to accurately forecast LTU spells and outperforms the rule-based model by offering robust predictions that perform well under stress tests. This paper presents the first performance comparison between a complex, currently implemented, rule-based approach and complex statistical profiling models. Our work illustrates the importance of assessing the calibration of profiling models and the potential of statistical tools to assist public employment services." (Author's abstract, IAB-Doku) ((en))

Keywords: Katalonien; Spanien; Algorithmus; Langzeitarbeitslose; Langzeitarbeitslosigkeit; Modell; Profiling; Prognosegenauigkeit; Prognoseverfahren; schwervermittelbare Arbeitslose; statistische Methode; Machine learning; Arbeitsuchende; Arbeitsvermittlung; Arbeitsverwaltung; 2017-2023 (search for similar items in EconPapers)
JEL-codes: J08 J64 J68 (search for similar items in EconPapers)
Date: 2025-10-17
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1186/s12651-025-00399-w

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:iab:iabjlr:v:59:p:art.26

Ordering information: This journal article can be ordered from
https://www.springer.com/economics/journal/12651

DOI: 10.1186/s12651-025-00399-w

Access Statistics for this article

Journal for Labour Market Research is currently edited by Joachim Möller et al.

More articles in Journal for Labour Market Research from Institut für Arbeitsmarkt- und Berufsforschung (IAB), Nürnberg [Institute for Employment Research, Nuremberg, Germany] Contact information at EDIRC.
Bibliographic data for series maintained by IAB, Geschäftsbereich Informationsmanagement und Bibliothek ().