What the study found
The study found that a joint policy for matching orders to shoppers and setting delivery compensation can reduce delivery costs in a crowd-shipping system that uses in-store customers as couriers. The authors report that allowing multi-drop routing and flexible delivery delays also lowers operational costs.
Why the authors say this matters
The authors conclude that these results support dynamic, forward-looking policies for crowd-shipping systems. They say the findings offer practical guidance for urban logistics operators facing last-mile delivery needs.
What the researchers tested
The researchers studied a centralized crowd-shipping system in a brick-and-mortar retail setting, where shoppers were offered compensation to deliver time-sensitive online orders. They modeled uncertain order arrivals, uncertain crowd-shipper arrivals, and the chance that delivery offers would be accepted using a Markov Decision Process, or MDP, a mathematical framework for decision-making under uncertainty. Their solution combined Neural Approximate Dynamic Programming, or NeurADP, for order-to-shopper assignment with a Deep Double Q-Network, or DDQN, for dynamic pricing.
What worked and what didn't
The integrated NeurADP + DDQN policy achieved up to 6.7% savings compared with NeurADP using fixed pricing, and about 18% savings compared with myopic baselines. The study also reports that flexible delivery delays reduced operational costs by 8%, and multi-destination routing reduced them by 17%.
What to keep in mind
The abstract does not describe detailed limitations beyond the modeled assumptions and experimental setting. The findings are reported for a centralized retail crowd-shipping system and may be specific to the tested setup.
Key points
- The study examined crowd-shipping that uses in-store customers as delivery couriers.
- A joint assignment-and-pricing policy reduced delivery costs compared with fixed-pricing and myopic baselines.
- The reported savings were up to 6.7% versus NeurADP with fixed pricing and about 18% versus myopic baselines.
- Flexible delivery delays reduced costs by 8%.
- Multi-destination routing reduced costs by 17%.
Disclosure
- Research title:
- Joint pricing and matching lowered crowd-shipping delivery costs
- Authors:
- Arash Dehghan, Mücahit Çevik, Merve Bodur, Bissan Ghaddar
- Institutions:
- Maxwell Institute for Mathematical Sciences, Metropolitan University, Metropolitan University, University of Edinburgh, Western University
- Publication date:
- 2026-04-22
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.