Potential-Based Greedy Matching for Dynamic Delivery Pooling

TL;DR

This paper introduces a simple potential-based greedy algorithm for dynamic delivery pooling that improves efficiency by balancing immediate savings against future opportunities, outperforming naive methods and rivaling complex batching strategies.

Contribution

The paper proposes a novel potential-based greedy algorithm for delivery pooling, with theoretical guarantees and practical effectiveness demonstrated through extensive experiments.

Findings

PB achieves vanishing worst-case regret as market density increases.

PB outperforms naive greedy heuristics in real-world and synthetic data.

PB matches the performance of complex batching heuristics with lower computational costs.

Abstract

We study the dynamic pooling of multiple orders into a single trip, a strategy widely adopted by online delivery platforms. When an order has to be dispatched, the platform must determine which (if any) of the available orders to pool it with, weighing the immediate efficiency gains against the uncertain, differential benefits of holding each order for future pooling opportunities. In this paper, we demonstrate the effectiveness of using the delivery distance as a proxy for opportunity cost via a potential-based greedy algorithm (PB). The algorithm is simple, pooling each departing job with the available job that maximizes the immediate savings in travel distance minus "half its delivery distance", which we call the potential of the available job. Theoretically, we show that PB achieves vanishing worst-case regret per job as market density increases, whereas a naive greedy policy suffers constant regret. We further show that the potential approximates the true opportunity cost of dispatching a job, in a stochastic setting with sufficient density. Finally, we conduct extensive numerical experiments on both synthetic data and real-world data from the Meituan platform. Despite being forecast-agnostic, PB consistently outperforms greedy heuristics that rely on historical data. Moreover, PB achieves performance comparable to computationally-intensive batching heuristics, which themselves also benefit from incorporating the potential to further improve their performance or drastically reduce computational costs.