Guidelines for the computational testing of machine learning approaches to vehicle routing problems

Luca Accorsi; Andrea Lodi; Daniele Vigo

doi:10.1016/j.orl.2022.01.018

Guidelines for the computational testing of machine learning approaches to vehicle routing problems

Luca Accorsi
, Andrea Lodi
, Daniele Vigo^*

^*Corresponding author for this work

Research output: Contribution to Journal › Article › Academic › peer-review

424 Downloads (Pure)

Abstract

Despite the extensive research efforts and the promising results obtained by the ML community on Vehicle Routing Problems, most of the proposed techniques are still seldom employed by the OR community. With the current work, we highlight a number of challenges arising during the computational evaluation of heuristics for VRPs. The resulting guidelines aim at defining a common testing setup for the approaches designed by the two communities, thus promoting and strengthening the collaboration between them.

Original language	English
Pages (from-to)	229-234
Number of pages	6
Journal	Operations Research Letters
Volume	50
Issue number	2
Early online date	15 Feb 2022
DOIs	https://doi.org/10.1016/j.orl.2022.01.018
Publication status	Published - Mar 2022

Bibliographical note

Funding Information:
We gratefully thank a referee for its valuable comments and suggestions that greatly improved the quality of the manuscript.

Publisher Copyright:
© 2022 Elsevier B.V.

Funding

We gratefully thank a referee for its valuable comments and suggestions that greatly improved the quality of the manuscript.

Keywords

Computational testing
Machine learning
Vehicle routing

Access to Document

10.1016/j.orl.2022.01.018

Guidelines for the computational testing of machine learning approaches to vehicle routing problemsFinal published version, 360 KBLicence: Article 25fa Dutch Copyright Act

Persistent URL (handle)

Persistent link

Cite this

@article{28aede606b4041f68634b23d72c9e959,

title = "Guidelines for the computational testing of machine learning approaches to vehicle routing problems",

abstract = "Despite the extensive research efforts and the promising results obtained by the ML community on Vehicle Routing Problems, most of the proposed techniques are still seldom employed by the OR community. With the current work, we highlight a number of challenges arising during the computational evaluation of heuristics for VRPs. The resulting guidelines aim at defining a common testing setup for the approaches designed by the two communities, thus promoting and strengthening the collaboration between them.",

keywords = "Computational testing, Machine learning, Vehicle routing",

author = "Luca Accorsi and Andrea Lodi and Daniele Vigo",

note = "Funding Information: We gratefully thank a referee for its valuable comments and suggestions that greatly improved the quality of the manuscript. Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = mar,

doi = "10.1016/j.orl.2022.01.018",

language = "English",

volume = "50",

pages = "229--234",

journal = "Operations Research Letters",

issn = "0167-6377",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - Guidelines for the computational testing of machine learning approaches to vehicle routing problems

AU - Accorsi, Luca

AU - Lodi, Andrea

AU - Vigo, Daniele

PY - 2022/3

Y1 - 2022/3

N2 - Despite the extensive research efforts and the promising results obtained by the ML community on Vehicle Routing Problems, most of the proposed techniques are still seldom employed by the OR community. With the current work, we highlight a number of challenges arising during the computational evaluation of heuristics for VRPs. The resulting guidelines aim at defining a common testing setup for the approaches designed by the two communities, thus promoting and strengthening the collaboration between them.

AB - Despite the extensive research efforts and the promising results obtained by the ML community on Vehicle Routing Problems, most of the proposed techniques are still seldom employed by the OR community. With the current work, we highlight a number of challenges arising during the computational evaluation of heuristics for VRPs. The resulting guidelines aim at defining a common testing setup for the approaches designed by the two communities, thus promoting and strengthening the collaboration between them.

KW - Computational testing

KW - Machine learning

KW - Vehicle routing

UR - https://www.scopus.com/pages/publications/85126060137

UR - https://www.scopus.com/pages/publications/85126060137#tab=citedBy

U2 - 10.1016/j.orl.2022.01.018

DO - 10.1016/j.orl.2022.01.018

M3 - Article

AN - SCOPUS:85126060137

SN - 0167-6377

VL - 50

SP - 229

EP - 234

JO - Operations Research Letters

JF - Operations Research Letters

IS - 2

ER -

Guidelines for the computational testing of machine learning approaches to vehicle routing problems

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this