ScienceDirect® Home Skip Main Navigation Links
You have guest access to ScienceDirect. Find out more.
 
Home
Browse
My Settings
Alerts
Help
 Quick Search
 Search tips (Opens new window)
    Clear all fields    
advertisementadvertisement
Electronic Commerce Research and Applications
Volume 6, Issue 3, Autumn 2007, Pages 285-296
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Article
Purchase PDF (252 K)

  E-mail Article   
  Add to my Quick Links   
Bookmark and share in 2collab (opens in new window)
Request permission to reuse this article
  Cited By in Scopus (0)
 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/j.elerap.2006.06.001    How to Cite or Link Using DOI (Opens New Window)
Copyright © 2006 Elsevier B.V. All rights reserved.

The design and evaluation of an intelligent sales agent for online persuasion and negotiation

Shiu-li Huanga, 1, E-mail The Corresponding Author and Fu-ren Linb, Corresponding Author Contact Information, E-mail The Corresponding Author

aDepartment of Information Management, School of Information Technology, Ming Chuan University, 5 Teh-Ming Road, Gwei-Shan District, Taoyuan County 333, Taiwan, ROC bGraduate Institute of Technology Management, College of Technology Management, National Tsing Hua University, 101 Section 2, Kuang-Fu Road, Hsinchu 300, Taiwan, ROC

Received 2 April 2006; 
accepted 22 June 2006. 
Available online 14 July 2006.

Purchase the full-text article



References and further reading may be available for this article. To view references and further reading you must purchase this article.

Abstract

Online purchases from e-stores are getting popular among Internet users. Although many e-commerce activities, such as auctions, bargaining, and recommendation services are available, most e-stores lack clerk-like mechanisms to persuade potential buyers into buying products and to bargain with them for making a good deal. The objectives of this research are to design a lab prototype of a sales agent with persuasion and negotiation capabilities and to evaluate its effectiveness as a virtual clerk in an e-store. The prototypical intelligent sales agent (ISA) is equipped with reinforcement learning capabilities and an abstract argument framework. We conduct both laboratory and Internet experiments to assess ISA’s performance. The experimental results reveal that an e-store embedded within such a sales agent can improve a seller’s surplus and increase a buyer’s product valuation, willingness-to-pay, and satisfaction with the e-store.

Keywords: Abstract argumentation framework; Negotiation; Persuasion; Reinforcement learning; Sales agent

Article Outline

1. Introduction
2. Literature review
2.1. Negotiation agent and persuasion agent
2.2. Reinforcement learning
2.3. Abstract argumentation framework
2.4. Why customers are willing to pay more
3. The architecture of ISA
4. Hypotheses
5. Experimental procedure
5.1. Training ISA’s persuasion ability by simulation games
5.2. Training ISA’s negotiation ability by simulation games
5.3. Training ISA by interaction with humans
5.4. Laboratory experiment
5.5. Internet experiment
6. Experimental results
6.1. Results of laboratory experiment
6.2. Results of an internet experiment
7. Conclusions
Acknowledgements
Appendix. An example of human–agent dialogue via ISA
References






 
Home
Browse
My Settings
Alerts
Help
Elsevier.com (Opens new window)
About ScienceDirect  |  Contact Us  |  Information for Advertisers  |  Terms & Conditions  |  Privacy Policy
Copyright © 2008 Elsevier B.V. All rights reserved. ScienceDirect® is a registered trademark of Elsevier B.V.