The evaluation of intelligent agent performance — An example of B2C e-commerce negotiation

doi:10.1016/j.csi.2012.02.003

Computer Standards & Interfaces

Volume 34, Issue 5, September 2012, Pages 439-446

https://doi.org/10.1016/j.csi.2012.02.003 Get rights and content

Abstract

Increasing demand for sophisticated software capable to collaborate, control, and organize all distributed activities has encouraged researchers in various disciplines to utilize and implement Intelligent Agent (IA). This paper develops a methodology to appraise performance of the IA and demonstrate the use in the B2C e-commerce negotiation process. An experiment was conducted to acquire empirical data and a survey was implemented to confirm advantage of the use of the IA. The computational results indicate that the proposed approach successfully evaluates IA performance and significantly distinguishes groups of using (vs. not using) the negotiation mechanism in B2C e-commerce.

Highlights

► Regulate, control, and organize all distributed activities by IAs. ► Apply an intelligent agent to B2C EC negotiation to optimize financial resources. ► Experiment data is acquired and a questionnaire is conducted. ► The results show that IA systems improve the performance of negotiation systems.

Introduction

Increasing demand for sophisticated software capable to collaborate, control, and organize all distributed activities has encouraged researchers in various disciplines to utilize and implement IA. IA can help users perform actions involving inquiries, negotiation, and tradeoffs to improve effectiveness. Among them, negotiation is an inseparable component of many e-commerce activities, such as auctions, scheduling, and contracting, and is one area that can benefit markedly from automation [38]. However, negotiation in B2C is time-consuming due to all parties anticipate to maximize their profit and likely they may have opposing consequences. When some parties do not compromise, reaching an agreement is impossible [10]. The IA is a new approach for e-negotiations. Using IA to represent negotiating parties can greatly decrease the effort and time needed to complete negotiations [17].

Recent research in IA has primarily focused on developing technologies in the agent systems. For example, Morge and Beaune [32] developed an agent-based negotiation support system that has the following functionalities: information sharing among stakeholders; auto-negotiation between agents; and, group decision-making modeling. Moreover, Louta et al. [30] proposed a dynamic multi-lateral negotiation model and constructed an efficient negotiation strategy based on a ranking mechanism. Recently, Lee et al. [27] analyzed the data with an agent-based procurement system (APS) to re-engineer and improve the existing procurement process while Huang et al. [17] present a multiple-attributes negotiation model for B2C ecommerce. This model deploys intelligent agents to facilitate autonomous and automatic on-line buying and selling by intelligent agents while quickly responding to consumers. Using IA in e-commerce negotiation applications are enormous [14]. However, very little research has appraised performance of the IA to validate contribution and an active role of the IA, especially in the area of B2C e-commerce.

This study develops a methodology to appraise performance of the IA and demonstrate the use in the B2C e-commerce negotiation process. An experiment was conducted to acquire empirical data and a survey was implemented to confirm advantage of the use of the IA. This paper is organized as follows: In Section 2, the literature review of B2C e-commerce and intelligent agent performance evaluation is illustrated. The research method used in this paper is proposed in Section 3. Then, data analysis is described in Section 4. Section 5 concludes the paper.

Section snippets

B2C e-commerce

Business-to-consumer (B2C) is similar in concept to the traditional method of retailing, the main difference being the medium used to carry out business — the Internet [1]. By directly to customers and reducing the middlemen rake, the company could lower prices and then in consultation with customers to obtain greater benefits [15]. Besides, [16] developed a goal-driven methodology for eliciting and modeling the requirements of a B2C application, it enables business managers and system

Research method

The principal aim of the study is to verify the effectiveness of intelligent agent systems in B2C e-commerce. This study uses an experimental desig1n to compare differences in using and not using the intelligent agent system. Additionally, a questionnaire is used to assess the effectiveness of the intelligent agent system via participant responses.

Data analysis

Data were analyzed using SPSS version 12.0. Statistical methods used for questionnaire of the customer satisfaction analysis were the Kolmogorov–Smirnov test, reliability analysis, validity analysis and T-tests. This study used T-tests to implement test hypotheses.

Conclusion

Per literature review in agent based study, numerous references can be found in designing agents for automated negotiation. However, few studies have evaluated performance of the intelligent agent and validate contribution of the IA. This research applies intelligent agent to B2C e-Commerce negotiation. An experiment was used to conduct the evaluation. Results show that intelligent agent do improve performance of the negotiation process. The questionnaire of customer satisfaction analysis

Acknowledgments

This work was partially supported by funding from the National Science Council of the Republic of China (NSC 99-2410-H-018-016-MY3; NSC 98-2410-H-260-011-MY3; NSC 99-2410-H-260-051-MY3).

Wen-Yau Liang is a professor of Information Management at National Changhua University of Education. He received his Ph.D. from the University of Iowa. His research interests are object-oriented design, artificial intelligence, intelligent agent, data mining and electronic commerce. He has published research papers in journals sponsored by various societies.

References (45)

C.J. Anumba et al.
Electronic commerce in construction-trends and prospects
Automation in Construction
(2002)
P. Argoneto et al.
Production planning, negotiation and coalition integration: A new tool for an innovative e-business model
Robotics and Computer-Integrated Manufacturing
(2010)
G. Beydoun
Formal concept analysis for an e-learning semantic web
Expert Systems with Applications
(2009)
E.D. Boudreaux et al.
The Dynamic Assessment and Referral System for Substance Abuse (DARSSA): Development, functionality, and end-user satisfaction
Drug and Alcohol Dependence
(2009)
C.C. Chan et al.
Electronic Commerce Research and Applications
(2007)
S.P.M. Choi et al.
A genetic agent-based negotiation system
Computer Networks
(2001)
P. Faratin et al.
Negotiation decision functions for autonomous agents
Robotics and Autonomous Systems
(1998)
D.G. Gregg et al.
Auction Advisor: an agent-based online-auction decision support system
Decision Support Systems
(2006)
S.C. Ho et al.
A growth theory perspective on B2C e-commerce growth in Europe: An exploratory study
Electronic Commerce Research and Applications
(2007)
T.-L. Hsia et al.
The e-commerce value matrix and use case model: A goal-driven methodology for eliciting B2C application requirements
Journal of Information Management
(2008)

C.C. Huang et al.

The agent-based negotiation process for B2C e-commerce

Expert Systems with Applications

(2010)

S.L. Huang et al.

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

Electronic Commerce Research and Applications

(2007)

H. Kahramanli et al.

Extracting rules for classification problems: AIS based approach

Expert Systems with Applications

(2009)

H. Kim et al.

The impact of website quality on information quality, value, and loyalty intentions in apparel retailing

Journal of Interactive Marketing

(2009)

S. Kwon et al.

Reservation price reporting mechanisms for online negotiations

Decision Support Systems

(2009)

R.Y.K. Lau et al.

Knowledge discovery for adaptive negotiation agents in e-marketplaces

Decision Support Systems

(2008)

C.K.M. Lee et al.

Design and development of agent-based procurement system to enhance business intelligence

Expert Systems with Applications

(2009)

F.R. Lin et al.

Integrating multi-agent negotiation to resolve constraints in fulfilling supply chain orders

Electronic Commerce Research and Applications

(2006)

P. Litzelfelner

Consumer satisfaction with CASAs (Court Appointed Special Advocates)

Children and Youth Services Review

(2008)

U. Manzoor et al.

An agent based system for activity monitoring on network – ABSAMN

Expert Systems with Applications

(2009)

S. Moulet et al.

The influence of seller learning and time constraints on sequential bargaining in an artificial perishable goods market

Journal of Economic Dynamics and Control

(2008)

E.W.T. Ngai

Learning in Introductory E-Commerce: A Project-Based Teamwork Approach

Computers in Education

(2007)

Cited by (16)

A mathematical model with flexible negotiation strategies for agent based negotiations in dynamic e-commerce environments
2018, Journal of King Saud University - Computer and Information Sciences
In this paper, a mathematical model with flexible negotiation strategies for agent based negotiations is developed which can be applied suitably in bilateral/multilateral multi-issue negotiation environments. Unlike the existing approaches for offer value computation for the negotiation issues, this model considers not only the reservation values but also the offer values proposed in the preceding negotiation round. This approach for offer value computation enables the traders to reach consensus much quicker than the existing approaches. This model considers the compelling urge of the trader in buying/selling a product based on which the reservation values are adjusted automatically at the end of the negotiation process in order to reach consensus in a deal which is otherwise not possible. The formula devised in this model to determine the concession speed of each negotiation issue handles the dynamicity of the negotiation environment and reflects the importance of each negotiation issue from the traders’ perspective. The effectiveness of the proposed strategies is evaluated using various hypothetical cases representing the real-world negotiation scenarios in an e-commerce environment. The test results show that the proposed negotiation strategies are able to optimize the utility process and also improve the rate of reaching consensus in the negotiation process.
Electronic supply chains: Status & perspective
2015, Computers and Industrial Engineering
The area of e-commerce based supply chains (or e-supply chains) has received significant attention in the last two decades. Despite the high level of activity, the most recent reviews on this topic date back to the beginning of this century. In this paper, we analyzed the state of e-supply chain research published during January 2000–January 2015 AD, covering 165 articles from 47 ISI indexed journals. The analysis is performed using a five-dimensional framework comprising Topic-of-Study, Unit-of-Analysis, Research Perspective, Industry Type, and Research Method. Within these dimensions, Topic-of-Study plays a pivotal role, whereas the other four dimensions are analyzed around its sub-classification scheme. Our main objective is to establish a broader interdisciplinary understanding of the e-supply chain research domain, and to identify trends and gaps in contemporary e-supply chain theory and practice. The findings indicate that problems are addressed from different perspectives with varying levels of interest from researchers belonging to several academic disciplines including business, economics, engineering and social sciences. Our analysis also identified two distinct periods (2000–2006 and 2007 onwards) with different foci of research attention. The problems that received significant attention in the earlier period include innovation, adoption and barriers, and supply chain integration; while in the latter period, the focus seemed to have shifted towards supply chain integration and collaboration issues. Problems that received minimum interest across the two periods include customer relationship, economic and environmental impact.
BROSEMWEB: A brokerage service for e-Procurement using Semantic Web Technologies
2014, Computers in Industry
Citation Excerpt :
The objective of this effort was focused in clearly define the system requirements with a single purpose: to maximize the system functionality or usefulness with available resources. In order to define the user's requirements, the team behind BROSEMWEB extracted the common requirements reported in technical literature [1,4,9,11,14,22,26,30]. The requirements under evaluation were: (R1) B2B collaboration, (R2) Management of business processes, (R3) Monitor business interactions, (R4) Semantic Web Services, (R5) Event publish/subscription mechanism, (R6) Messaging service, (R7) Repository Mechanism, and (R8) Semantic Web Service Discovery.
The Service-Oriented-Architecture (SOA) development paradigm has emerged to make an improvement in critical situations such as creating, modifying and extending solutions in the domain of business processes integration. Web services technologies are considered as the main units for SOA, for both intra- and inter-enterprise communication. Nevertheless, SOA does not have information about the events that occurs in business processes, which represents the main characteristics of supply chain management. Taking this into account, this paper proposes a middleware-oriented integrated architecture with the use of semantic features (concretely with the use of Linked Data) as data provider to offer a brokerage service for the procurement of products in a Supply Chain Management (SCM). As main contributions, our system provides a hybrid architecture that combines features of both SOA and EDA between several others.
Efficient communication architecture for the C2C agent
2014, Computer Standards and Interfaces
Citation Excerpt :
Consumers have to spend much time searching and scanning to find products which achieve their demands. It can be seen that although users can get a lot of information, it will take much time to filter useful information [12,16]. If users can collect all needed information before communication, the time should be reduced.
In C2C communication, all necessary information must be collected promptly when a buyer and a seller communicate. That is, an intelligent C2C agent is needed to provide information to buyers and sellers. Along with the evolution of computing technology, C2C agents can exploit the efficient delivery capabilities of peer-to-peer (P2P) technology. However, P2P also increases traffic between agents, but communication faults are a fatal problem for C2C business. This study proposes a robust communication architecture based on current P2P content-delivery standards and its efficiency and robustness have been verified from an experiment.
A topic-based recommender system for electronic marketplace platforms
2013, Expert Systems with Applications
Citation Excerpt :
Some tasks presented in this paper are covered in the literature by agent-based systems, where computational models simulate the actions and interactions of autonomous agents, while other work uses mathematical and machine learning models. A methodology is suggested for employing the use of an intelligent agent in a negotiation process, and its application is demonstrated in the case of negotiation between companies and clients (Liang, Huang, Tseng, Lin, & Tseng, 2012). The experimental evaluation confirms the advantages of the use of such systems.
A large number of items are described, and subsequently bought and sold every day in auction marketplaces across the web. The amount of information and the number of available items makes finding what to buy as well as describing an item to sell, a challenge for the participants. In this paper we consider two functions of electronic marketplaces. First, we address the recommendation of related items for users browsing the items offered in a marketplace. Second, in order to support potential sellers we propose the recommendation of relevant items and terms which can be used to describe an item to be sold in the marketplace. The contribution of this paper lies in the proposal of an innovative system that exploits the hidden topics of unstructured information found in the e-marketplace in order to support these functions. We propose a three-step process in which a probabilistic topic modelling approach is used in order to uncover latent topics that provide the basis for item and term similarity calculation for the corresponding recommendations. We present the design of our system and perform evaluations of the quality of the extracted topics as well as of the recommender system using real life scenarios using data extracted from a widely used auction marketplace. The evaluations demonstrate the perceived usefulness of our approach.
Automated negotiation in open and distributed environments
2013, Expert Systems with Applications
Citation Excerpt :
The authors propose an agent based approach to support negotiation in catalogue based e-marketplace, managing the trade among buyers and sellers, taking into account their identities and goals, and providing better global satisfaction. Liang, Huang, Tseng, Lin, and Tseng (2012) integrates the automated negotiation techniques into B2C e-commerce applications. They conduct experiments and survey to analysis the advantage of using automated negotiation agents in B2C e-commerce, compared to those who do not use.
Automated negotiation is one of the most common approaches used to make decisions and manage disputes between computational entities leading them to optimal agreements. Many existing works tackle single-issue negotiations and the negotiation environment is assumed to be static so that the agents can make decisions based solely on the proposals of the counterparts and their own fixed parameters. Most real-world scenarios, however, involve complex domains and dynamic environments. In such cases, it is no longer sufficient to consider negotiation as an isolated activity in a static environment. Therefore, a more general framework for automated negotiation is needed in which the negotiation agents can be very flexible and adaptive. In this paper, we describe a generic framework for automated negotiation, which captures descriptively the social dynamics of the negotiation process. The proposed framework enables the agents to behave responsively to the changes in the environment. Their strategies can adapt as the conditions outside of the negotiation change to ensure that their decisions remain rational. And the agents are proactive and responsive by searching for options, which are outside of the negotiation and which may improve their outcomes. The key ideas and the overall system architecture together with a specific negotiation instance in a basic bilateral setting are described, along with two illustrative examples. The first example is in the context of e-commerce, and the second example is an application scenario of service level agreement negotiation in service computing. We also describe a prototypical implementation of the proposed negotiation framework.

View all citing articles on Scopus

Chun-Che Huang received his Ph.D. degree in Industrial Engineering from the University of Iowa, Iowa City, and his M.S. degree in Operations Research from Columbia University, New York, NY. He is a Professor in the Department of Information Engineering, National Chi Nan University, Taiwan and directs the Laboratory of Intelligent Systems and Knowledge Management (the ISKM Lab.). He is interested in intelligent systems, knowledge management, and data mining. He has published research papers in journals sponsored by various societies.

Tzu-Liang (Bill) Tseng is an associate professor of Industrial, Manufacturing and Systems Engineering at the University of Texas at El Paso (UTEP). He received his M.S. degree in Decision Sciences at the University of Wisconsin-Madison and his Ph.D. degree in Industrial Engineering at the University of Iowa. His research focuses on computational intelligence, data mining, bio- informatics and advanced manufacturing. Dr. Tseng published in many refereed journals such as IEEE Transactions, IIE Transaction, Journal of Manufacturing Systems and others. He has been serving as a principle investigator of many research projects, funded by NSF, NASA, DoEd, and KSEF. He is currently serving as an editor of the Journal of Computer Standards & Interfaces.

Yin-Chen Lin was awarded a Master's degree in Information Management from the National Changhua University of Education in 2009.

Juotzu Tseng was awarded a Master's degree in Information Management from the National Changhua University of Education in 2011. She is currently working toward a Ph.D degree in Information Management at the National Central University, Taiwan.

View full text

The evaluation of intelligent agent performance — An example of B2C e-commerce negotiation

Abstract

Highlights

Introduction

Section snippets

B2C e-commerce

Research method

Data analysis

Conclusion

Acknowledgments

Automation in Construction

Robotics and Computer-Integrated Manufacturing

Expert Systems with Applications

Drug and Alcohol Dependence

Electronic Commerce Research and Applications

Computer Networks

Robotics and Autonomous Systems

Decision Support Systems

Electronic Commerce Research and Applications

Journal of Information Management

Expert Systems with Applications

Electronic Commerce Research and Applications

Expert Systems with Applications

Journal of Interactive Marketing

Decision Support Systems

Decision Support Systems

Expert Systems with Applications

Electronic Commerce Research and Applications

Children and Youth Services Review

Expert Systems with Applications

Journal of Economic Dynamics and Control

Computers in Education