Detecting and Forecasting Economic Regimes in Multi-Agent Automated Exchanges

31 Pages Posted: 27 Nov 2007

See all articles by Wolfgang Ketter

Wolfgang Ketter

University of Cologne - Institute of Energy Economics; Erasmus University Rotterdam (EUR) - Department of Technology and Operations Management; Erasmus Research Institute of Management (ERIM)

John Collins

University of Minnesota - Twin Cities

Maria Gini

University of Minnesota - Twin Cities - Computer Science and Engineering

Alok Gupta

University of Minnesota - Twin Cities - Carlson School of Management

Paul Schrater

University of Minnesota - Twin Cities

Date Written: October 19, 2007

Abstract

We show how an autonomous agent can use observable market conditions to characterize the microeconomic situation of the market and predict future market trends. The agent can use this information to make both tactical decisions, such as pricing, and strategic decisions, such as product mix and production planning. We develop methods to learn dominant market conditions, such as over-supply or scarcity, from historical data using Gaussian mixture models to construct price density functions. We discuss how this model can be combined with real-time observable information to identify the current dominant market condition and to forecast market changes over a planning horizon. We forecast market changes 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 the next day (supporting tactical decisions), while the Markov correction-prediction 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.

Keywords: dynamic pricing, machine learning, market forecasting, Trading agents

Suggested Citation

Ketter, Wolfgang and Collins, John and Gini, Maria L and Gupta, Alok and Schrater, Paul, Detecting and Forecasting Economic Regimes in Multi-Agent Automated Exchanges (October 19, 2007). ERIM Report Series Reference No. ERS-2007-065-LIS, Available at SSRN: https://ssrn.com/abstract=1032747

Wolfgang Ketter (Contact Author)

University of Cologne - Institute of Energy Economics ( email )

Alte Wagenfabrik
Vogelsanger Strasse 321a
Cologne, 50827
Germany

HOME PAGE: http://ewi.uni-koeln.de/en/

Erasmus University Rotterdam (EUR) - Department of Technology and Operations Management ( email )

RSM Erasmus University
PO Box 1738
3000 DR Rotterdam
Netherlands

Erasmus Research Institute of Management (ERIM) ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands

HOME PAGE: http://www.rsm.nl/energy

John Collins

University of Minnesota - Twin Cities ( email )

420 Delaware St. SE
Minneapolis, MN 55455
United States

Maria L Gini

University of Minnesota - Twin Cities - Computer Science and Engineering ( email )

200 Union St SE, #4-192
Minneapolis, MN 55455
United States

HOME PAGE: http://www,cs,umn.edu/~gini

Alok Gupta

University of Minnesota - Twin Cities - Carlson School of Management ( email )

19th Avenue South
Minneapolis, MN 55455
United States

Paul Schrater

University of Minnesota - Twin Cities ( email )

420 Delaware St. SE
Minneapolis, MN 55455
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
96
Abstract Views
1,200
rank
335,093
PlumX Metrics