Fleet size planning in crowdsourced delivery: Balancing service level and driver utilization
Bibliographic record
Abstract
This paper addresses the fleet size planning problem for crowdsourced delivery platforms, focusing on optimizing the number of crowdsourced drivers to balance the platform’s service level and driver utilization. This is motivated by recent regulatory measures that limit the number of vehicle licenses a platform can hold, which caps fleet size as a means to enhance driver working conditions and mitigate congestion and emissions caused by an excessive number of idle vehicles on the road. We propose a two-stage optimization model where the first stage involves tactical decisions for determining fleet sizes, while the second stage captures the operational dynamics of the platform by a Markov decision process (MDP) in which uncertain crowd driver arrival in the MDP depends on fleet size decisions in the first stage, introducing decision-dependent uncertainty. To efficiently solve the model, we employ a value function approximation (VFA) algorithm that iteratively determines fleet sizes using Boltzmann exploration then approximates the second-stage MDP using a rolling-horizon parametric cost function approximation. Extensive computational experiments confirm the effectiveness of the VFA algorithm, demonstrating its ability to meet both service level and driver utilization targets under various conditions. The results show that a platform can achieve high driver utilization and meet its service level target while only marginally reducing its profit, especially when driver behavior is more predictable and fleet sizes are temporally adjusted.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".