Analytics and machine learning in vehicle routing research

The Vehicle Routing Problem (VRP) is one of the most intensively studied combinatorial optimisation problems for which numerous models and algorithms have been proposed. To tackle complexities, uncertainties dynamics involved in real-world VRP applications, Machine Learning (ML) methods used combination with analytical approaches to enhance problem formulations algorithmic performance across different solving scenarios. However, relevant papers are scattered several traditional research fields very different, sometimes confusing, terminologies. This paper presents a first, comprehensive review hybrid that combine techniques ML tools addressing problems. Specifically, we emerging streams on ML-assisted modelling optimisation. We conclude can be beneficial enhancing modelling, improving both online offline optimisations. Finally, challenges future opportunities discussed.