Improving Learning Performance By Applying Economic Knowledge

AGENT-MEDIATED ELECTRONIC COMMERCE V: DESIGNING MECHANISMS AND SYSTEMS(LECTURE NOTES IN COMPUTER SCIENCE), Vol. 3048, P. Faratin, D.C. Parkes, J.A. Rodríguez-Aguilar, W.E. Walsh, eds., Springer-Verlag, 2004

Posted: 7 Apr 2007

See all articles by Christopher H. Brooks

Christopher H. Brooks

University of San Francisco

Robert S. Gazzale

University of Toronto - Department of Economics; Williams College - Department of Economics

Jeffrey K. MacKie-Mason

UC Berkeley; University of Michigan

Edmund Durfee

University of Michigan at Ann Arbor - Department of Electrical Engineering and Computer Science

Abstract

Digital information economies require information goods producers to learn how to position themselves within a potentially vast product space. Further, the topography of this space is often nonstationary, due to the interactive dynamics of multiple producers changing their positions as they try to learn the distribution of consumer preferences and other features of the problem's economic structure. This presents a producer or its agent with a difficult learning problem: how to locate profitable niches in a very large space. In this paper, we present a model of an information goods duopoly and show that, under complete information, producers would prefer not to compete, instead acting as local monopolists and targeting separate niches in the consumer population. However, when producers have no information about the problem they are solving, it can be quite difficult for them to converge on this solution. We show how a modest amount of economic knowledge about the problem can make it much easier, either by reducing the search space, starting in a useful area of the space, or by introducing a gradient. These experiments support the hypothesis that a producer using some knowledge of a problem's (economic) structure can outperform a producer that is performing a naive, knowledge-free form of learning.

Suggested Citation

Brooks, Christopher H. and Gazzale, Robert S. and MacKie-Mason, Jeffrey K. and Durfee, Edmund, Improving Learning Performance By Applying Economic Knowledge. AGENT-MEDIATED ELECTRONIC COMMERCE V: DESIGNING MECHANISMS AND SYSTEMS(LECTURE NOTES IN COMPUTER SCIENCE), Vol. 3048, P. Faratin, D.C. Parkes, J.A. Rodríguez-Aguilar, W.E. Walsh, eds., Springer-Verlag, 2004, Available at SSRN: https://ssrn.com/abstract=978067

Christopher H. Brooks (Contact Author)

University of San Francisco ( email )

2130 Fulton Street
San Francisco, CA 94117
United States

Robert S. Gazzale

University of Toronto - Department of Economics ( email )

150 St. George Street
Toronto, Ontario M5S 3G7
Canada
416.978.2123 (Phone)

HOME PAGE: http://www.economics.utoronto.ca/gazzale/

Williams College - Department of Economics ( email )

24 Hopkins Hall Drive
Williamstown, MA 01267
United States

Jeffrey K. MacKie-Mason

UC Berkeley ( email )

102 South Hall
Berkeley, CA 94720-4600
United States

HOME PAGE: http://jeff-mason.com

University of Michigan ( email )

Ann Arbor, MI 48109-1092
United States

HOME PAGE: http://http:/jeff-mason.com/

Edmund Durfee

University of Michigan at Ann Arbor - Department of Electrical Engineering and Computer Science ( email )

1101 Beal Avenue
Ann Arbor, MI 48109
United States

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

Paper statistics

Abstract Views
381
PlumX Metrics