Trustworthy and Explainable Decision-Making for Workforce allocation
Guillaume Povéda, Ryma Boumazouza, Andreas Strahl, Mark Hall, Santiago Quintana-Amate, Nahum Alvarez, Ignace Bleukx, Dimos Tsouros, Hélène Verhaeghe, Tias Guns
TL;DR
The paper tackles trustworthy, explainable workforce allocation by integrating constraint programming with interactive, user-guided infeasibility handling. It defines a CP model for assigning teams to scheduled tasks, and introduces MUS/MCS-based explainability plus conflict visualization to illuminate infeasibilities. A CPMpy-based prototype demonstrates optimization performance across instance sizes and showcases a Streamlit demonstrator for solving, refining solutions, and interactive feasibility restoration. The work highlights the potential to increase trust and acceptance of CP-based decision tools in industry, with planned user studies, interface enhancements, and extension to scheduling-shifting scenarios to address scalability and realism.
Abstract
In industrial contexts, effective workforce allocation is crucial for operational efficiency. This paper presents an ongoing project focused on developing a decision-making tool designed for workforce allocation, emphasising the explainability to enhance its trustworthiness. Our objective is to create a system that not only optimises the allocation of teams to scheduled tasks but also provides clear, understandable explanations for its decisions, particularly in cases where the problem is infeasible. By incorporating human-in-the-loop mechanisms, the tool aims to enhance user trust and facilitate interactive conflict resolution. We implemented our approach on a prototype tool/digital demonstrator intended to be evaluated on a real industrial scenario both in terms of performance and user acceptability.