Search

In ride-sharing systems, platform providers aim to distribute the drivers in the city to meet current and potential future demand and to avoid service cancellations. Ensuring such distribution is particularly challenging in the case of a crowdsourced fleet, as drivers are not centrally controlled but are free to decide where to reposition when idle. Thus, providers look for alternative ways to ensure a vehicle distribution that benefits users, drivers, and the provider. We propose an intuitive mean to improve idle ride-sharing vehicles' repositioning: repositioning heatmaps. These heatmaps highlight driver-specific earning opportunities approximated based on the expected future demand, current and expected future fleet distribution, and the location of the specific driver. Based on the heatmaps, drivers make decentralized yet better-informed repositioning decisions. As our heatmap policy changes the driver distribution in the future, we propose an adaptive learning algorithm for designing our heatmaps in large-scale ride-sharing systems. We simulate the system and generate heatmaps based on the previously learned policy in every iteration. We then update the policy based on the simulation's outcome and use it in the next iteration. We test our heatmap design in a comprehensive case study on New York ride-sharing data. We show that carefully designed heatmaps reduce service cancellations and therefore, revenue loss for the platform and drivers significantly while leading to a better service level for the users and to a fairer treatment of drivers. History: This paper has been accepted for the Transportation Science Special Issue on Machine Learning Methods and Applications in Large-Scale Route Planning Problems. Funding: This research is funded by the German Research Foundation (Deutsche Forschungsgemeinschaft) [Grant 494812908]. M. W. Ulmer's work is funded by the German Research Foundation Emmy Noether Programme [Grant 444657906]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2023.1202. [ABSTRACT FROM AUTHOR]

The ongoing growth of e‐commerce deliveries has led to a significant increase in last‐mile delivery volumes. New technologies are being investigated to provide these deliveries efficiently and in a customer‐friendly manner. A common practice is to use fixed parcel lockers (FPLs) to make deliveries independent from the presence of the customer as is the case in attended home deliveries (AHDs). FPLs are usually installed at key locations in cities, and customers can collect their package at any time once it has been delivered to this particular location. Mobile parcel lockers (MPLs) represent a new idea: they can be parked for temporary collection of items at different locations, keeping the pickup distance to the customer short and avoiding high infrastructure costs. However, customers need to collect their parcels within a restricted time window. This service is supposed to become especially efficient through autonomously operating vehicles that can move MPLs at low costs. In this article, we introduce the heterogeneous locker location problem to study the effects of fleets combining two of the services—FPLs, MPLs, AHDs—within one framework. In our comparison, we consider that customers may have different expectations regarding their maximum pickup distance as well as their temporal flexibility in accepting deliveries. A fixed fleet is applied to maximize the number of customers served, respecting individual customer preferences in terms of pickup distances and time windows. We evaluate the different delivery services regarding managerial insights on service quality and efficiency. In the experiments, we analyze the impact of structural demand differences and different fleet sizes, as well as the operational fleet utilization and the individual customer experience. Results show the potential to increase the number of customers served by about 14%–19% through the use of MPLs while considering individual customer preferences. [ABSTRACT FROM AUTHOR]