One Dynamic Pricing Strategy in Agent Economy Using Neural Network Based on Online Learning

Authors:
Danxia Kong
Affiliations:
Brown University, Providence, RI
Venue:
WI '04 Proceedings of the 2004 IEEE/WIC/ACM International Conference on Web Intelligence
Year:
2004

Citing 1
Cited 1

Learning about other agents in a dynamic multiagent system

Cognitive Systems Research

A dynamic pricing approach in e-commerce based on multiple purchase attributes

AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper examines seller strategies for dynamic pricing in a market for which a seller has finite time horizon to sell its inventory. A dynamic pricing strategy is developed using neural network based on online learning (called SDNN strategy). The SDNN strategy takes in account the dynamics and resulting uncertainties of the market place. The experiments show that the SDNN strategy exhibits superior performance to the other candidate dynamic pricing strategies which of similar computational simplicity and lack of assumptions about the market place.