Machine Learning for Scheduling: A Paradigm Shift from Solver-Centric to Data-Centric Approaches

TL;DR

This paper reviews the shift from traditional solver-centric scheduling methods to modern data-centric machine learning approaches, emphasizing the benefits, design choices, and future research directions for adaptive, reliable scheduling systems.

Contribution

It provides a comprehensive framework for understanding the transition to data-driven scheduling, comparing different learning mechanisms, and outlining a research agenda for scalable and trustworthy solutions.

Findings

Machine learning enhances scheduling efficiency and flexibility.

End-to-end learning directly generates scheduling solutions from data.

Trade-offs exist between scalability, interpretability, and generalization.

Abstract

Scheduling problems are a fundamental class of combinatorial optimization problems that underpin operational efficiency in manufacturing, logistics, and service systems. While operations research has traditionally developed solver-centric methods emphasizing model structure and optimality, recent advances in machine learning are reshaping scheduling toward a more data-centric approach that leverages experience and enables fast decision-making in dynamic environments. This paper offers a framework-based synthesis and perspective on this methodological transition. We use the paradigm shift from solver-centric optimization to data-centric learning as a unifying lens to organize and interpret a rapidly expanding literature. We first briefly revisit classical optimization-based approaches and discuss how machine learning has been integrated to improve computational efficiency and guide search while retaining solver-based feasibility and accountability. We then synthesize end-to-end learning approaches that generate scheduling solutions (or solution-generating policies) directly from data, clarifying the key design choices in solution generation and feasibility handling. Building on these organizing frameworks, we compare learning mechanisms and training signals (supervised, self-supervised, and reinforcement learning) in terms of scalability, interpretability, and generalization, and highlight the trade-offs that matter for reliable deployment. Finally, we outline an agenda along three interdependent dimensions, scalability, reliability, and universality, that together define a pathway toward adaptive, intelligent, and trustworthy scheduling systems for data-driven operations management.