Home > Research > Publications & Outputs > Choice-based Crowdshipping for Next-day Deliver...

Electronic data

  • EJORChoice_4_

    Accepted author manuscript, 830 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Forthcoming

Standard

Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem. / Arslan, Alp; Kilci, Firat; Cheng, Shih-Fen et al.
In: European Journal of Operational Research, 22.05.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Arslan, A., Kilci, F., Cheng, S.-F., & Misra, A. (in press). Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem. European Journal of Operational Research. https://doi.org/10.1016/j.ejor.2025.05.046

Vancouver

Arslan A, Kilci F, Cheng SF, Misra A. Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem. European Journal of Operational Research. 2025 May 22. doi: 10.1016/j.ejor.2025.05.046

Author

Arslan, Alp ; Kilci, Firat ; Cheng, Shih-Fen et al. / Choice-based Crowdshipping for Next-day Delivery Services : A Dynamic Task Display Problem. In: European Journal of Operational Research. 2025.

Bibtex

@article{8b50e812d66c44d78056ed752c68364b,
title = "Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem",
abstract = "This paper studies integrating the crowd workforce into next-day home delivery services. In this setting, both crowd drivers and contract drivers collaborate in making deliveries. Crowd drivers have limited capacity and can choose not to deliver if the presented tasks do not align with their preferences. The central question addressed is: How can the platform minimize the total task fulfilment cost, which includes payouts to crowd drivers and additional payouts to contract drivers for delivering the unselected tasks by customizing task displays to crowd drivers? To tackle this problem, we formulate it as a finite-horizon Stochastic Decision Problem, capturing crowd drivers{\textquoteright} utility-driven task preferences, with the option of not choosing a task based on the displayed options. An inherent challenge is approximating the non-constant marginal cost of serving orders not chosen by crowd drivers, which are then assigned to contract drivers. We address this by leveraging a common approximation technique, dividing the service region into zones. Furthermore, we devise a stochastic look-ahead strategy that tackles the curse of dimensionality issues arising in dynamic task display execution and a non-linear (problem specifically concave) boundary condition associated with the cost of hiring contract drivers. In experiments inspired by Singapore{\textquoteright}s geography, we demonstrate that choice-based crowd shipping can reduce next-day delivery fulfilment costs by up to 16.9%. The observed cost savings are closely tied to the task display policies and the task choice behaviours of drivers.",
author = "Alp Arslan and Firat Kilci and Shih-Fen Cheng and Archan Misra",
year = "2025",
month = may,
day = "22",
doi = "10.1016/j.ejor.2025.05.046",
language = "English",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Choice-based Crowdshipping for Next-day Delivery Services

T2 - A Dynamic Task Display Problem

AU - Arslan, Alp

AU - Kilci, Firat

AU - Cheng, Shih-Fen

AU - Misra, Archan

PY - 2025/5/22

Y1 - 2025/5/22

N2 - This paper studies integrating the crowd workforce into next-day home delivery services. In this setting, both crowd drivers and contract drivers collaborate in making deliveries. Crowd drivers have limited capacity and can choose not to deliver if the presented tasks do not align with their preferences. The central question addressed is: How can the platform minimize the total task fulfilment cost, which includes payouts to crowd drivers and additional payouts to contract drivers for delivering the unselected tasks by customizing task displays to crowd drivers? To tackle this problem, we formulate it as a finite-horizon Stochastic Decision Problem, capturing crowd drivers’ utility-driven task preferences, with the option of not choosing a task based on the displayed options. An inherent challenge is approximating the non-constant marginal cost of serving orders not chosen by crowd drivers, which are then assigned to contract drivers. We address this by leveraging a common approximation technique, dividing the service region into zones. Furthermore, we devise a stochastic look-ahead strategy that tackles the curse of dimensionality issues arising in dynamic task display execution and a non-linear (problem specifically concave) boundary condition associated with the cost of hiring contract drivers. In experiments inspired by Singapore’s geography, we demonstrate that choice-based crowd shipping can reduce next-day delivery fulfilment costs by up to 16.9%. The observed cost savings are closely tied to the task display policies and the task choice behaviours of drivers.

AB - This paper studies integrating the crowd workforce into next-day home delivery services. In this setting, both crowd drivers and contract drivers collaborate in making deliveries. Crowd drivers have limited capacity and can choose not to deliver if the presented tasks do not align with their preferences. The central question addressed is: How can the platform minimize the total task fulfilment cost, which includes payouts to crowd drivers and additional payouts to contract drivers for delivering the unselected tasks by customizing task displays to crowd drivers? To tackle this problem, we formulate it as a finite-horizon Stochastic Decision Problem, capturing crowd drivers’ utility-driven task preferences, with the option of not choosing a task based on the displayed options. An inherent challenge is approximating the non-constant marginal cost of serving orders not chosen by crowd drivers, which are then assigned to contract drivers. We address this by leveraging a common approximation technique, dividing the service region into zones. Furthermore, we devise a stochastic look-ahead strategy that tackles the curse of dimensionality issues arising in dynamic task display execution and a non-linear (problem specifically concave) boundary condition associated with the cost of hiring contract drivers. In experiments inspired by Singapore’s geography, we demonstrate that choice-based crowd shipping can reduce next-day delivery fulfilment costs by up to 16.9%. The observed cost savings are closely tied to the task display policies and the task choice behaviours of drivers.

U2 - 10.1016/j.ejor.2025.05.046

DO - 10.1016/j.ejor.2025.05.046

M3 - Journal article

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

ER -