A Portfolio Strategy Design for Human-Computer Negotiations in e-Retail

ABSTRACT

Human–computer negotiation has the potential to play an important role in today’s highly dynamic online environment, especially in business-to-consumer e-commerce transactions. However, the lack of research on effective automated negotiation algorithms to respond to human buyers’ strategic and/or tactic offers has limited the development of automated human–computer negotiation systems for real-world applications. Intelligent software agents that are capable of dynamically adjusting their negotiation strategy in response to human buyers’ offers can greatly improve the negotiation experience of human buyers. In this study, guided by design science principles, we design a portfolio strategy model, which implements four negotiation strategies (i.e., time-dependent, behavior-dependent, dynamic time-dependent, and impasse resolution) as the core of our software agent for negotiating with human buyers. To evaluate this novel model, we implement a prototype of the system and compare it with three benchmark single-strategy models (i.e., competitive, collaborative, and selection) in human–computer negotiation experiments. The results show that our model not only enables the software agent to outperform its human counterpart but also significantly increases the settlement ratio and the joint outcome of both parties.

KEY WORDS AND PHRASES:

• Electronic commerce
• automated negotiation
• negotiation strategy
• human–computer interaction
• design science
• human–computer negotiation
• software agents
• online negotiation

Acknowledgments

This work was supported by the China Scholarship Council (Grant# 201706315032), and the Natural Science Foundation of China (Grant# 71671154), and the Fundamental Research Funds for the Central Universities of China (Grant# 20720161052).

Notes

¹ Alibaba’s $30bn Singles’ Day shopping extravaganza smashes sales record. See https://gbtimes.com/alibabas-30bn-singles-day-shopping-extravaganza-smashes-sales-record.

² Worldwide Retail Ecommerce Sales Will Reach $1.915 Trillion This Year. See https://www.emarketer.com/Article/Worldwide-Retail-Ecommerce-Sales-Will-Reach-1915-Trillion-This-Year/1014369.

Additional information

Notes on contributors

Mukun Cao

Mukun Cao is an associate professor of management information systems at the School of Management, Xiamen University, China. He received his Ph.D. in MIS from the Harbin Institute of Technology, China. He was a visiting scholar to several universities in the United States, including College of Business Administration at California State University Long Beach, Pamplin College of Business, Virginia Polytechnic Institute and State University, Harvard Business School, and Babson College. His research interests include the development and applications of AI/machine learning techniques to e-commerce, including automated negotiation, agent theory, and software agent technologies. His research has appeared in Decision Support Systems, Journal of Electronic Commerce Research, and other journals.

Qing Hu

Qing Hu is Professor of Information Systems and Senior Associate Dean for Academic Affairs and Innovation in the Zicklin School of Business at Baruch College, the City University of New York. He earned his Ph.D. degree in computer information systems from the University of Miami. His research primarily focuses on cybersecurity and impact of IT on organizational strategy, culture, and performance. Dr. Hu has published more than 130 research articles in academic journals, conferences, and books and has been an invited speaker at universities and academic conferences around the world. His work has been published in Information Systems Research, Journal of Management Information Systems, MIS Quarterly, California Management Review, and other leading journals.

Melody Y. Kiang

Melody Y. Kiang is a professor of computer information systems at California State University, Long Beach. She received her Ph.D. in MSIS from the University of Texas at Austin. Her research interests include the development and applications of AI/Machine Learning techniques to a variety of business problems and e-commerce-related research. Her research has appeared in Information Systems Research, Management Science, Journal of Management Information Systems., Decision Support Systems, and other journals. She is editor-in-chief of the Journal of Electronic Commerce Research.

Hong Hong

Hong Hong is an associate professor in the School of Management at Harbin Institute of Technology. She received her Ph.D. degree from the School of Management at Xiamen University. Her research interests include Internet finance, social media and electronic commerce. She has published in Decision Support Systems, Journal of Electronic Commerce Research, and the proceedings of Pacific Asia Conference on Information Systems, Americas Conference on Information Systems, and Hawaii International Conference on System Sciences.