Guidelines for the Computational Testing of Machine Learning approaches to Vehicle Routing Problems

TL;DR

This paper discusses the challenges in computational testing of machine learning methods for vehicle routing problems, aiming to bridge the gap between ML and operations research communities through improved evaluation practices.

Contribution

It identifies key challenges in evaluating ML approaches to VRPs and proposes guidelines to enhance the comparability and rigor of computational studies.

Findings

Highlights differences in evaluation methods between ML and OR communities

Proposes guidelines for standardized computational testing of VRP algorithms

Aims to foster collaboration between ML and OR researchers

Abstract

Despite the extensive research efforts and the remarkable results obtained on Vehicle Routing Problems (VRP) by using algorithms proposed by the Machine Learning community that are partially or entirely based on data-driven analysis, most of these approaches are still seldom employed by the Operations Research (OR) community. Among the possible causes, we believe, the different approach to the computational evaluation of the proposed methods may play a major role. With the current work, we want to highlight a number of challenges (and possible ways to handle them) arising during the computational studies of heuristic approaches to VRPs that, if appropriately addressed, may produce a computational study having the characteristics of those presented in OR papers, thus hopefully promoting the collaboration between the two communities.