Speaker: Dr. Michalis Deligiannis
Date: Thursday, 19 March 2026, Time: 13:00
Place: Conference Room, Department of Mechanical Engineering, Sekeri Street, Volos
Also Microsoft Teams meeting https://teams.microsoft.com/meet/33958600018363?p=j3SRzX8FWUDO4quK3I, Meeting ID: 339 586 000 183 63, Passcode: y8RC7X2X
Abstract:
We study a finite-horizon dynamic wholesale-price contract between a manufacturer and a retailer who observe only realized sales rather than true demand. Because stockouts censor unmet demand, both parties update a common posterior from shared sales data and interact in an incomplete-information dynamic Stackelberg game. We characterize Markov perfect equilibria using the public belief as the state variable. For Weibull demand, we extend the scaling approach to this strategic learning setting, prove equilibrium existence, and reduce computation to a standardized one-parameter recursion. For exponential demand, we prove that the equilibrium is unique and computable by backward induction. The numerical analysis reveals several distinctive features of the dynamic equilibrium. First, equilibrium wholesale prices are strictly increasing along feasible public-belief paths, including along censored transitions, whereas myopic wholesale prices are only weakly increasing. Second, at a fixed wholesale price, the retailer’s forward-looking best response may lie either below or above the myopic benchmark, because the marginal continuation value of additional information may be negative. Nevertheless, the equilibrium order quantity remains above the myopic equilibrium order because the manufacturer sets a lower equilibrium wholesale price early on to stimulate learning. Third, channel efficiency displays a pronounced nonlinear horizon effect: decentralization losses shrink rapidly as the horizon increases and then flatten for long horizons. Together, these results show how censored-demand learning shapes dynamic pricing, ordering, and supply-chain efficiency.
Speaker Bio:
Michalis Deligiannis is a Postdoctoral Researcher in the Department of Economics and Finance at Luiss Guido Carli University in Rome. He holds a PhD in Production and Operations Management from the Department of Mechanical Engineering of the University of Thessaly. He also holds a bachelor’s degree in mathematics and a master’s degree in Statistics and Modeling from the Aristotle University of Thessaloniki. His research focuses on dynamic decision-making within the fields of Operations Management and Supply Chain Management. Utilizing tools from stochastic dynamic optimization, game theory, and queueing theory, he studies topics such as inventory management, supplier selection under uncertainty, and competition in markets with heterogeneous customers. He has worked as a researcher at Eindhoven University of Technology (TU/e) in the Netherlands and possesses teaching experience in subjects such as Data Science and Supply Chain Coordination. His work has been published in leading international scientific journals, including the European Journal of Operational Research, the International Journal of Production Economics, and Omega.
This lecture is part of the seminar series of the MSc Program in Supply Chain Management and Logistics of the Department of Mechanical Engineering.