We show how an autonomous agent can use observable market conditions to characterize the microeconomic situation of the market and predict market trends. The agent can use this information for tactical decisions, such as pricing, and strategic decisions, such as product mix and production planning. We present methods to learn dominant market conditions, such as over-supply or scarcity, from historical data using Gaussian mixture models. We show how this model combined with real-time observable information is used to identify the current dominant market condition and to forecast market changes over a planning horizon. Market changes are forecast via both a Markov correction-prediction process and an exponential smoother. Empirical analysis shows that the exponential smoother yields more accurate predictions for the current and next day (supporting tactical decisions), while the Markov process is better for longer term predictions (supporting strategic decisions). Our approach offers more flexibility than traditional regression based approaches, since it does not assume a fixed functional relationship between dependent and independent variables. We validate our methods by presenting experimental results in a case study, the Trading Agent Competition for Supply Chain Management.
Bibliographical noteFunding Information:
Paul R. Schrater received the Ph.D. degree in Neuroscience from the University of Pennsylvania in 1999. Currently he is Assistant Professor of Psychology and Computer Science & Eng. at the University of Minnesota and head of the Computational Perception and Action Laboratory. His research interests involve probabilistic models of perception, control and learning in man and machine. He has published over 50 journal and conference papers in the above areas (twenty refereed journal papers). He has received grants from NIH, NSF, and ONR.
- Agent-mediated electronic commerce
- Dynamic pricing
- Machine learning
- Market forecasting
- Trading agents