Abstract
The coordination of order policies constitutes a great challenge in supply chain inventory management as various stochastic factors increase its complexity. Therefore, analytical approaches to determine a policy that minimises overall inventory costs are only suitable to a limited extent. In contrast, we adopt a heuristic approach, from the domain of artificial intelligence (AI), namely, Monte Carlo tree search (MCTS). To the best of our knowledge, MCTS has neither been applied to supply chain inventory management before nor is it yet widely disseminated in other branches of operations research. We develop an offline model as well as an online model which bases decisions on real-time data. For demonstration purposes, we consider a supply chain structure similar to the classical beer game with four actors and both stochastic demand and lead times. We demonstrate that both the offline and the online MCTS models perform better than other previously adopted AI-based approaches. Furthermore, we provide evidence that a dynamic order policy determined by MCTS eliminates the bullwhip effect.
Highlights
The supply chain management literature spans a wide range of topics, such as facility location, production, scheduling, transportation, return of goods, forecasting, and inventory management, this last being the main subject of this paper
We extend the category of Genetic Algorithms to the broader category of Evolutionary Algorithms, which offer a whole family of nature-inspired algorithms contributing to artificial intelligence (Floreano and Mattiussi 2008)
We investigate how Monte Carlo tree search (MCTS)-based policies perform compared to policies generated by Genetic Algorithms (GAs) and reinforcement learning (RL)
Summary
The supply chain management literature spans a wide range of topics, such as facility location, production, scheduling, transportation, return of goods, forecasting, and inventory management, this last being the main subject of this paper. Crucial is the coordination of order policies, the determination of an order policy in an integrated manner (Li and Wang 2007). This effort is hampered by the bullwhip effect, which refers to increasing order variability when moving up the supply chain. Examples of this effect occurring in industry can be found, e.g. in Lee et al (1997) and Fransoo and Wouters (2000). An appropriate order policy should minimise overall inventory costs, and aim at mitigating or even eliminating the bullwhip effect, albeit these two goals are often interrelated
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
