A strategy for improved satisfaction of selling software agents in E-commerce

  • Authors:
  • Thomas Tran;Robin Cohen

  • Affiliations:
  • School of Computer Science, University of Waterloo, Waterloo, ON, Canada;School of Computer Science, University of Waterloo, Waterloo, ON, Canada

  • Venue:
  • AI'03 Proceedings of the 16th Canadian society for computational studies of intelligence conference on Advances in artificial intelligence
  • Year:
  • 2003

Quantified Score

Hi-index 0.01

Visualization

Abstract

In this paper, we present a model for buying and selling agents in electronic marketplaces, based on reputation modelling and reinforcement learning. We take into account the fact that multiple selling agents may offer the same good with different quality and that selling agents may alter the quality of their goods in order to satisfy individual buyers. In our approach, buying agents learn to maximize the expected value of goods by dynamically maintaining sets of reputable and disreputable sellers. Selling agents learn to maximize their expected profits by adjusting prices and optionally altering the quality of their goods. In this paper, we focus on presenting experimental results that confirm the improved satisfaction of selling agents following the proposed selling algorithm. This work therefore demonstrates a valuable strategy for selling agents to follow in marketplaces where buyers model reputation.