Robust personnel rostering: how accurate should absenteeism predictions be?
This work addresses roster robustness for organizations like hospitals, but it is incremental as it builds on existing predict-then-optimize methods.
The paper tackles the problem of personnel rostering disruptions due to absenteeism by proposing a methodology to evaluate roster robustness using a predict-then-optimize approach with simulated predictions, showing it outperforms non-data-driven policies in a nurse rostering case study, particularly when employees have interchangeable skills.
Disruptions to personnel rosters caused by absenteeism often necessitate last-minute adjustments to the employees' working hours. A common strategy to mitigate the impact of such changes is to assign employees to reserve shifts: special on-call duties during which an employee can be called in to cover for an absent employee. To maximize roster robustness, we assume a predict-then-optimize approach that uses absence predictions from a machine learning model to schedule an adequate number of reserve shifts. In this paper we propose a methodology to evaluate the robustness of rosters generated by the predict-then-optimize approach, assuming the machine learning model will make predictions at a predetermined prediction performance level. Instead of training and testing machine learning models, our methodology simulates the predictions based on a characterization of model performance. We show how this methodology can be applied to identify the minimum performance level needed for the model to outperform simple non-data-driven robust rostering policies. In a computational study on a nurse rostering problem, we demonstrate how the predict-then-optimize approach outperforms non-data-driven policies under reasonable performance requirements, particularly when employees possess interchangeable skills.