Using an intelligent agent to classify competitor behavior and develop an effective E-market counterstrategy

Authors:
Bryan M. Hertweck;Terry R. Rakes;Loren Paul Rees
Affiliations:
Information Systems, Earl N. Philips School of Business, High Point University, High Point, NC 27262, USA;Business Information Technology, Pamplin College of Business, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA;Business Information Technology, Pamplin College of Business, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA
Venue:
Expert Systems with Applications: An International Journal
Year:
2010

Citing 5
Cited 0

Dynamic pricing by software agents

Computer Networks: The International Journal of Computer and Telecommunications Networking - electronic commerce
Modular Neural Network Classifiers: A Comparative Study

Journal of Intelligent and Robotic Systems
Learning Curve: A Simulation-Based Approach to Dynamic Pricing

Electronic Commerce Research
Dynamic Consumer Profiling and Tiered Pricing Using Software Agents

Electronic Commerce Research
Dynamic Pricing on the Internet: Importance and Implications for Consumer Behavior

International Journal of Electronic Commerce

Quantified Score

Hi-index	12.05

Visualization

Abstract

Internet markets allow online sellers to rapidly update prices. By employing intelligent software agents known as pricebots, the re-pricing process can be streamlined and automated. Developing the pricebot re-pricing logic requires an understanding of the optimal pricing strategy in relation to competitors' strategies. We use simulation to construct a decision table of the most effective counterstrategy for several competitor strategy combinations. We then design a neural network for classifying the strategies of the competition, which allows us to look up the optimal counterstrategy in the decision table. Our findings indicate that a pricebot armed with the decision table and neural network classifier can recognize when the market is such that no entrant can gain a profit advantage beyond the profit achieved at a common price floor, and in other cases where higher profits are possible, the agent is able to achieve statistically significant profit improvements over the no-pricebot case.