Tactical and Strategic Sales Management for Intelligent Agents Guided By Economic Regimes

Dr. Wolfgang Ketter, Erasmus University, The Netherlands.

Hosts: Professor D. Liu (Gatton College) and Professor J. Goldsmith (Computer Science).


Abstract:

Computing technology has radically defined supply chain operations from integrating supply chains via Enterprise Resource Planning (ERP) software to aggregating demand and supply through web based portals. Another set of tools that are beginning to appear in supply chain software are tools for decision support. However, technology continues to provide new opportunities, and new technology supported mechanisms are continuously being developed. This talk presents building blocks of economic theory based software agents that use their awareness and ability to predict economic conditions to make tactical decisions, such as product pricing, and strategic decisions, such as level of finished goods inventories. We combine economic principles with machine learning to characterize economic regimes that represent microeconomic conditions reflecting economic environments such as over-supply and scarcity. Our software agent uses real-time observable information to identify the current dominant market condition and can forecast regime changes over a future time period of interest, for example over a predefined planning horizon. We present models and computational approaches that can be used to characterize regimes and show how the regime prediction can be used to predict prices, price trends, and the probability of receiving a customer order in a supply chain environment characterized by oligopolistic market, multiple buyers and dynamic pricing. We validate our methods by presenting experimental results from a testbed derived from the Trading Agent Competition for Supply Chain Management (TAC SCM). The results show that our method outperforms traditional short- and long-term predictive modeling approaches. The talk will further highlight TAC Energy − a new Trading Agent Competition game for agent-based energy management.


Short Bio:

Wolfgang Ketter is Assistant Professor at the Department of Decision and Information Sciences at the Rotterdam School of Management of the Erasmus University. He received his Ph.D. in Computer Science from the University of Minnesota in 2007. He founded and runs the Learning Agents Research Group at Erasmus (LARGE)). The primary objective of LARGE is to research, develop, and apply autonomous and mixed-initiative intelligent agent systems to support human decision making in the area of business networks, electronic markets, and supply-chain management. He was co-chairing the TADA workshop at AAAI 2008, the general chair of TAC 2009, and is the chair of the board of directors of the association for trading agent research since 2010. He is the program co-chair of the International Conference of Electronic Commerce 2011. His research has been published in various information systems, and computer science journals such as AI Magazine, Decision Support Systems, Electronic Commerce Research and Applications, European Journal of Information Systems, INFORMS OR/MS Today, and International Journal of Electronic Commerce. He serves on the editorial board of Electronic Commerce Research and Applications. His current projects include:
DFA: Agent-based Decision-making in the Dutch Flower Auctions
TAC SCM: Autonomous Agents for Supply-Chain Management
TAC Energy: Trading Agent Competition for Energy Management

Related papers:

Paper 1 
Paper 2 
Paper 3