Research question
After an order is canceled, how can a delivery service coordinate pricing and reassignment to an alternative customer?
Approach and decision mechanism
The paper treats cancellation as a sequential routing and pricing decision. It formulates the Dynamic Routing and Pricing Problem with Cancellation as a route-based Markov decision process and develops a proximal policy optimization approach for learning the decision policy.
- CancellationAn order is canceled and the delivery plan needs to change.
- Pricing & reassignmentChoose a price and consider an alternative customer for the canceled order.
- Routing responseUpdate the delivery plan in response to the reassignment decision.
Pricing, customer reassignment, and routing are coupled. A recovery decision changes the delivery state and the revenue opportunities available in subsequent decisions.
Evidence and scope
Computational experiments compare the proposed approach with selected benchmarks across scenarios with uncertainty.
The reported evidence comes from the modeled delivery scenarios. Performance in another service depends on customer responses, cancellation patterns, and operating conditions.
Read the publication recordCite this paper
Deng, Y., Yan, Y., Chow, A. H. F., Zhou, Z., Ying, C., & Kuo, Y.-H. (2024). A proximal policy optimization approach for food delivery problem with reassignment due to order cancellation. Expert Systems with Applications, 258, 125045. https://doi.org/10.1016/j.eswa.2024.125045
View BibTeX
@article{deng2024food,
title = {A proximal policy optimization approach for food delivery problem with reassignment due to order cancellation},
author = {Yang Deng and Yimo Yan and Andy H.F. Chow and Zhili Zhou and Cheng-shuo Ying and Yong-Hong Kuo},
journal = {Expert Systems with Applications},
year = {2024},
volume = {258},
pages = {125045},
doi = {10.1016/j.eswa.2024.125045},
url = {https://doi.org/10.1016/j.eswa.2024.125045}
}