Transparent and fair profiling in employment services: evidence from Switzerland
Data & Policy · 2026 · 8
DOI: 10.1017/dap.2026.10070 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data & Policy, online erschienen am 24.06.2026. Verfasst von Tim Räz. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0). Gefördert von: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.
Abstract (Originalsprache)
Long-term unemployment (LTU) is a challenge for both jobseekers and public employment services. Statistical profiling tools are increasingly used to predict LTU risk. Some profiling tools are opaque, black-box machine learning (ML) models, which raise issues of transparency and fairness. The present paper investigates whether interpretable models could serve as an alternative, using administrative data from Switzerland. Traditional statistical, interpretable, and black-box models are compared in terms of predictive performance, interpretability, and fairness. It is shown that explainable boosting machines, a recent interpretable model, perform nearly as well as the best black-box models. It is also shown how model sparsity, feature smoothing, and fairness mitigation can enhance transparency and fairness with only minor losses in performance. These findings suggest that interpretable profiling provides an accountable and trustworthy alternative to black-box models without compromising performance.
Förderung
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Zitieren
APA
Räz, T. (2026). Transparent and fair profiling in employment services: evidence from Switzerland. Data & Policy, 8. https://doi.org/10.1017/dap.2026.10070
Vancouver
Räz T. Transparent and fair profiling in employment services: evidence from Switzerland. Data & Policy. 2026;8. doi:10.1017/dap.2026.10070
BibTeX
@article{Rz2026,
author = {Räz, Tim},
title = {Transparent and fair profiling in employment services: evidence from Switzerland},
journal = {Data & Policy},
year = {2026},
volume = {8},
doi = {10.1017/dap.2026.10070}
}
EUVIMED