Robust personnel rostering: how accurate should absenteeism predictions be?

TL;DR

This paper presents a methodology to evaluate how accurate absenteeism predictions need to be for a predict-then-optimize personnel rostering approach to outperform traditional policies, demonstrated through a nurse rostering case study.

Contribution

It introduces a simulation-based evaluation method for assessing the robustness of predict-then-optimize rostering strategies without training machine learning models.

Findings

Predict-then-optimize outperforms non-data-driven policies at reasonable prediction accuracy levels.

Interchangeable skills among employees enhance the effectiveness of the approach.

The methodology helps determine the minimum prediction accuracy required for improved robustness.

Abstract

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.