Anticipating delays in recruitment: explainable machine learning for the prediction of hard- to-fill online job vacancies
Anticipating delays in recruitment: explainable machine learning for the prediction of hard- to-fill online job vacancies
Online job vacancy (OJV) platforms have transformed the labor market by enabling employers to advertise jobs to a wide audience. Particularly in tight labor markets, quickly identifying vacancies likely to suffer prolonged durations is crucial. This study utilizes data from the Flemish public employment service's OJV platform to examine the effectiveness of machine learning in predicting hard-to-fill vacancies. We achieve notable predictive performance with XGBoost in forecasting recruitment delays and demonstrate the importance of capturing non-linear patterns in OJV data. SHAP (SHapley Additive exPlanations) values reveal that the textual content of vacancies and latent company characteristics are key predictors of hiring delays. Counterfactual-SHAP insights provide practical guidance for refining recruitment strategies, enhancing labor market forecasts, and informing targeted policies.
Analytics, Decision support systems, Machine learning, Natural language processing, Online job vacancies
680-693
Dossche, Wouter
d31e5e3a-5a25-4cd0-b665-214366bb5e77
Vansteenkiste, Sarah
b01dc6fb-109d-44e3-b28d-b7a753afce8f
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Lemahieu, Wilfried
be4bae3f-12b9-417a-91a1-c3c264ffe068
Dossche, Wouter
d31e5e3a-5a25-4cd0-b665-214366bb5e77
Vansteenkiste, Sarah
b01dc6fb-109d-44e3-b28d-b7a753afce8f
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Lemahieu, Wilfried
be4bae3f-12b9-417a-91a1-c3c264ffe068
Dossche, Wouter, Vansteenkiste, Sarah, Baesens, Bart and Lemahieu, Wilfried
(2025)
Anticipating delays in recruitment: explainable machine learning for the prediction of hard- to-fill online job vacancies.
European Journal of Operational Research, 328 (2), .
(doi:10.1016/j.ejor.2025.06.027).
Abstract
Online job vacancy (OJV) platforms have transformed the labor market by enabling employers to advertise jobs to a wide audience. Particularly in tight labor markets, quickly identifying vacancies likely to suffer prolonged durations is crucial. This study utilizes data from the Flemish public employment service's OJV platform to examine the effectiveness of machine learning in predicting hard-to-fill vacancies. We achieve notable predictive performance with XGBoost in forecasting recruitment delays and demonstrate the importance of capturing non-linear patterns in OJV data. SHAP (SHapley Additive exPlanations) values reveal that the textual content of vacancies and latent company characteristics are key predictors of hiring delays. Counterfactual-SHAP insights provide practical guidance for refining recruitment strategies, enhancing labor market forecasts, and informing targeted policies.
Text
Revised manuscript clean version
- Accepted Manuscript
Restricted to Repository staff only until 24 June 2027.
Request a copy
More information
Accepted/In Press date: 23 June 2025
e-pub ahead of print date: 24 June 2025
Keywords:
Analytics, Decision support systems, Machine learning, Natural language processing, Online job vacancies
Identifiers
Local EPrints ID: 503619
URI: http://eprints.soton.ac.uk/id/eprint/503619
ISSN: 0377-2217
PURE UUID: fc4f6bf3-c38b-48b7-959f-2a98f336cb1c
Catalogue record
Date deposited: 07 Aug 2025 16:36
Last modified: 10 Oct 2025 16:53
Export record
Altmetrics
Contributors
Author:
Wouter Dossche
Author:
Sarah Vansteenkiste
Author:
Wilfried Lemahieu
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
