Scheduling multi-configuration last-mile delivery logistics by learning from optimisation feedback and customer preferences

Basit Öğe Kaydı
dc.authorscopusidReza Tavakkoli-Moghaddam / 57207533714
dc.authorwosidReza Tavakkoli-Moghaddam / P-1948-2015
dc.contributor.authorTafakkori, Keivan
dc.contributor.authorTavakkoli-Moghaddam, Reza
dc.contributor.authorSiadat, Ali
dc.date.accessioned2025-06-18T13:23:15Z
dc.date.available2025-06-18T13:23:15Z
dc.date.issued2025
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Endüstri Mühendisliği Bölümü
dc.description.abstractLast-mile delivery (LMD) logistics employ multiple delivery process configurations (e.g. depot-micro, depot-self, and depot-home) to meet the delivery time expectations of customers on a large scale. Meanwhile, scheduling delivery visits within multi-configuration LMD logistics requires solving complex, integrated, and intractable mathematical models. This paper presents a deep neuroevolution from an optimisation feedback algorithm that enables one to solve a set of decomposed configuration-based mathematical models instead. The algorithm trains a predictive model (e.g. a deep neural network) to learn to assign customers to each configuration. Then, feedback is deduced by solving a set of decomposed prescriptive models to schedule deliveries within each configuration. A single objective is minimised considering total delivery time, earliness and tardiness of deliveries, arrival deviation, and total and maximum self-pickup time. The pre-trained predictive model is compared with a surrogate prescriptive assignment model regarding computational time and optimisation feedback. The applicability of the proposed algorithm is validated by a set of stability and scalability tests based on Amazon's LMD case study. The predictive model is found to outperform the simple assignment model in 100% of the test instances. In addition, its ability to grasp contextual attributes of multiple sides in LMD logistics and generalisation is highlighted.
dc.identifier.citationTafakkori, K., Tavakkoli-Moghaddam, R., & Siadat, A. (2025). Scheduling multi-configuration last-mile delivery logistics by learning from optimisation feedback and customer preferences. International Journal of Production Research, 1-30.
dc.identifier.doi10.1080/00207543.2025.2507795
dc.identifier.endpage30
dc.identifier.issn0020-7543
dc.identifier.issn1366-588X
dc.identifier.scopus2-s2.0-105005837677
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttp://dx.doi.org/10.1080/00207543.2025.2507795
dc.identifier.urihttps://hdl.handle.net/20.500.12713/7318
dc.identifier.wosWOS:001493476400001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorTavakkoli-Moghaddam, Reza
dc.institutionauthoridReza Tavakkoli-Moghaddam / 0000-0002-6757-926X
dc.language.isoen
dc.publisherTaylor and francis ltd.
dc.relation.ispartofInternational journal of production research
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectDeep Reinforcement Learning
dc.subjectLast-Mile Delivery Scheduling
dc.subjectLearning-Based Decomposition
dc.subjectMultiple Configurations
dc.subjectPre-Trained Predictive Model
dc.titleScheduling multi-configuration last-mile delivery logistics by learning from optimisation feedback and customer preferences
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
Scheduling multi-configuration last-mile delivery logistics by learning from optimisation feedback and customer preferences.pdf
Boyut:
4.1 MB
Biçim:
Adobe Portable Document Format
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

Endüstri Mühendisliği Bölümü Makale Koleksiyonu