Transportation Service Procurement Bid Construction Problem from Less Than Truckload Perspective

Yan, Fang; Ma, Yanfang; Xu, Manjing; Ge, Xianlong

doi:10.1155/2018/1728512

Cited by 7 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, we highlight related works on optimal bidding in freight transport; in most of these studies competing carriers bid on transport jobs. For instance, Yan et al (2018) propose a particle swarm optimization algorithm to place carrier bids on jobs. Miller and Nie (2020) emphasize the importance of integrating carrier competition, routing and bidding.…”

Section: Literature Reviewmentioning

confidence: 99%

Strategic bidding in freight transport using deep reinforcement learning

Heeswijk¹

2022

Ann Oper Res

View full text Add to dashboard Cite

This paper presents a multi-agent reinforcement learning algorithm to represent strategic bidding behavior by carriers and shippers in freight transport markets. We investigate whether feasible market equilibriums arise without central control or communication between agents. Observed behavior in such environments serves as a stepping stone towards self-organizing logistics systems like the Physical Internet, while also offering valuable insights for the design of contemporary transport brokerage platforms. We model an agent-based environment in which shipper and carrier actively learn bidding strategies using policy gradient methods, posing bid- and ask prices at the individual container level. Both agents aim to learn the best response given the expected behavior of the opposing agent. Inspired by financial markets, a neutral broker allocates jobs based on bid-ask spreads. Our game-theoretical analysis and numerical experiments focus on behavioral insights. To evaluate system performance, we measure adherence to Nash equilibria, fairness of reward division and utilization of transport capacity. We observe good performance both in predictable, deterministic settings ($$\sim $$ ∼ 95% adherence to Nash equilibria) and highly stochastic environments ($$\sim $$ ∼ 85% adherence). Risk-seeking behavior may increase an agent’s reward share, yet overly aggressive strategies destabilize the system. The results suggest a potential for full automation and decentralization of freight transport markets. These insights ease the design of real-world market platforms, suggesting an innate tendency of markets to reach equilibria without behavioral models, information sharing or explicit incentives.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Strategic bidding in freight transport using deep reinforcement learning

Heeswijk¹

2022

Ann Oper Res

View full text Add to dashboard Cite

show abstract

“…(Olcaytu and Kuyzu, 2019) contributed to the literature on price estimation in spot truckload markets by the development of load-specific truckload price-estimating methods and measuring their effect on the cost-effectiveness of carriers participating in the transportation network. In another study, bidders (carriers) generate their best bid (package) by using a bundled price to make the most of their utility and enhance the chance of winning the business via mixed integer programming for TSP (Yan et al, 2018b). An integrated multi-round combinatorial auction mechanism was developed for truckload TSP in which a winner determination problem was solved to assign profitable lanes to carriers (Kwon et al, 2005).…”

Section: Literature Reviewmentioning

confidence: 99%

Leader-based diffusion optimization model in transportation service procurement under heterogeneous drivers’ collaboration networks

2022

View full text Add to dashboard Cite

One of the key issues in transportation systems is allocating shipping orders to the most appropriate drivers, in the shortest time and with the maximum profit. Many studies were carried out in the transportation service procurement process for allocating orders, but none of them considered driver-to-driver interactions and applied information diffusion concepts as a framework to maximize the profit, due to the lack of a framework to model the interactions. In this paper, we present a weighted drivers' collaboration network to form the interactions. To predict the behavior of drivers, a new community detection algorithm is developed to extract communities and their leaders, in terms of the speed and the power of receiving and diffusing shipping orders. Also, we present a profit maximization model using information diffusion power of community leaders. The results show the model is able to allocate shipping orders to the most suitable drivers, in the best possible time and with the highest profit. To demonstrate the performance of the developed algorithm, we present a numerical example. Finally, a case study is applied to solve the optimization problem. The results show that the optimized behavior of companies in allocating orders to drivers is based on their risk level, reputation, and the average number of their customers.

show abstract

“…Next, we highlight related works on optimal bidding in freight transport; most of these studies seem to adopt a viewpoint in which competing carriers bid on transport jobs. For instance, Yan et al [30] propose a particle swarm optimization algorithm used by carriers to place bids on jobs. Miller & Nie [8] present a solution that emphasizes the importance of integrating carrier competition, routing and bidding.…”

Section: Literature Reviewmentioning

confidence: 99%

Strategic bidding in freight transport using deep reinforcement learning

Heeswijk¹

2021

Preprint

View full text Add to dashboard Cite

This paper presents a multi-agent reinforcement learning algorithm to represent strategic bidding behavior in freight transport markets. Using this algorithm, we investigate whether feasible market equilibriums arise without any central control or communication between agents. Studying behavior in such environments may serve as a stepping stone towards self-organizing logistics systems like the Physical Internet. We model an agent-based environment in which a shipper and a carrier actively learn bidding strategies using policy gradient methods, posing bid-and ask prices at the individual container level. Both agents aim to learn the best response given the expected behavior of the opposing agent. A neutral broker allocates jobs based on bid-ask spreads.Our game-theoretical analysis and numerical experiments focus on behavioral insights. To evaluate system performance, we measure adherence to Nash equilibria, fairness of reward division and utilization of transport capacity. We observe good performance both in predictable, deterministic settings (∼95% adherence to Nash equilibria) and highly stochastic environments (∼85% adherence). Risk-seeking behavior may increase an agent's reward share, as long as the strategies are not overly aggressive. The results suggest a potential for full automation and decentralization of freight transport markets.

show abstract

Transportation Service Procurement Bid Construction Problem from Less Than Truckload Perspective

Cited by 7 publications

References 30 publications

Strategic bidding in freight transport using deep reinforcement learning

Strategic bidding in freight transport using deep reinforcement learning

Leader-based diffusion optimization model in transportation service procurement under heterogeneous drivers’ collaboration networks

Strategic bidding in freight transport using deep reinforcement learning

Contact Info

Product

Resources

About