Enabling Sustainable Freight Forwarding Network via Collaborative Games

TL;DR

The paper tackles fragmentation in freight forwarding by introducing Locally Collaborative Games (LCG), a graph-restricted cooperative framework in which a player's marginal contribution is determined by its neighbors, enabling scalable Shapley value computation via FS-LCG. It defines the Freight Forwarders Collaboration Game (FFCG) as an instance of LCG and formulates the capacity-sharing problem as FFCP, solved with a greedy pre-solve followed by exact optimization. The authors show that FS-LCG significantly outperforms a prior general-purpose algorithm across various network topologies and yields meaningful cost savings for forwarders, highlighting the method's practical viability for large-scale, fragmented freight networks. Overall, the work contributes a scalable, fair-cost allocation mechanism for collaborative freight networks and demonstrates its applicability through numerical experiments.

Abstract

Freight forwarding plays a crucial role in facilitating global trade and logistics. However, as the freight forwarding market is extremely fragmented, freight forwarders often face the issue of not being able to fill the available shipping capacity. This recurrent issue motivates the creation of various freight forwarding networks that aim at exchanging capacities and demands so that the resource utilization of individual freight forwarders can be maximized. In this paper, we focus on how to design such a collaborative network based on collaborative game theory, with the Shapley value representing a fair scheme for profit sharing. Noting that the exact computation of Shapley values is intractable for large-scale real-world scenarios, we incorporate the observation that collaboration among two forwarders is only possible if their service routes and demands overlap. This leads to a new class of collaborative games called the Locally Collaborative Games (LCGs), where agents can only collaborate with their neighbors. We propose an efficient approach to compute Shapley values for LCGs, and numerically demonstrate that our approach significantly outperforms the state-of-the-art approach for a wide variety of network structures.

Figures (9)

• Figure 1: An LCG example.
• Figure 2: 10-agent LCG example.
• Figure 3: Request-service assignments decomposed into non-overlapping sub-problems.
• Figure 4: An FFCG example.
• Figure 5: Runtime in a general setting.