Anticipating delays in recruitment: Explainable machine learning for the prediction of hard-to-fill online job vacancies

•Machine learning framework for the early detection of hard-to-fill vacancies.•First to use embeddings for vacancy content and latent company characteristics.•Novel insights into the significant predictors of hard-to-fill vacancies.•Counterfactuals offer actionable advice to reduce the risk of hirin...

Full description

Saved in:
Bibliographic Details
Published in:European journal of operational research Vol. 328; no. 2; pp. 680 - 693
Main Authors: Dossche, Wouter, Vansteenkiste, Sarah, Baesens, Bart, Lemahieu, Wilfried
Format: Journal Article
Language:English
Published: Elsevier B.V 16.01.2026
Subjects:
Analytics
Decision support systems
Machine learning
Natural language processing
Online job vacancies
Decision support systems
Online job vacancies
Natural language processing
Analytics
Machine learning
ISSN:0377-2217
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Machine learning framework for the early detection of hard-to-fill vacancies.•First to use embeddings for vacancy content and latent company characteristics.•Novel insights into the significant predictors of hard-to-fill vacancies.•Counterfactuals offer actionable advice to reduce the risk of hiring delays. 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.
ISSN:0377-2217
DOI:10.1016/j.ejor.2025.06.027