Designing intelligent agents to support long-term partnership in two echelon e-Supply Networks Shima Mohebbi, Xueping Li ⇑ Department of Industrial and Information Engineering, University of Tennessee, Knoxville, TN 37996, USA article info Keywords: e-Supply Networks (e-SN) Intelligent agents Long-term partnership Supply chain coordination Multi-agent system (MAS) abstract Realizing the dynamic nature of information flow and the conflicting objectives of members play vital role in effective design of e-Supply Networks (e-SN). While there are some research in the SN literature proposing different dynamic and intelligent coordination mechanisms, the impact of the proper defini- tion of data structure and long-term relationship in modeling both coordination and negotiation mech- anisms have not been addressed deeply. In this paper, we propose three overlapping services including intelligent matching of partners, proposal generations, and long-term contract management. The process begins with the selection of qualified partners based on the similarity of users profiles in a multidimen- sional space defined by network attributes. Then, a coordination mechanism for long-term agreements is proposed such that the generated proposals in e-SN encourage buyers to reveal their demand in advance. The proposed mechanism introduces the importance of strategic buyers for suppliers in modeling and decision making process. To illustrate the model efficiency, a prototype system has been modeled and is compared to the traditional tendering mechanism. The validation results confirm the model efficiency in providing long-term decisions in a dynamic environment. Ó 2012 Elsevier Ltd. All rights reserved. 1. Introduction Recent Internet-based technologies such as web services pro- vide us with additional opportunity to deal with complex supply chains. For instance, information technology provides an infra- structure for integrating the internal and external activities of a company so that it connects the geographically distant supply chain members together to form a network system. In the same vein, electronic markets have eliminated the geographical obsta- cles and provided opportunities for the meaningful investigation of the buyer–supplier relationships in supply chains. Hence, the traditional linear supply chains are converted into an e-Supply Networks (e-SN) in which collaboration among partners, real-time decision making, and automation of conventional activities are improved. e-SN is an electronic-based, dynamic, and distributed supply system (Mohebbi, Shafaei, & Cho, 2011) comprised of many trans- actional echelons where the membership, the structure of interac- tion, and the nature of network attributes as represented by informational flow change dynamically over time (Mahdavi, Mohebbi, Zandakbari, Cho, & Mahdavi-Amiri, 2009). Indeed, an e- SN is comprised of independent input nodes, such as buyers with their corresponding information, influencing on each output node, i.e. suppliers, so that according to the input layer attributes and output layer capabilities in terms of the scope of work and avail- able capacity different flows can be obtained. Thus, it can be in- ferred that there is a couple of key factors affecting the success of an e-SN: (a) realizing the dynamic nature of information flow in a web-based environment and, (b) a proper cooperation mecha- nism among distributed supply network members. In an e-SN, new buyers and suppliers join, existing buyers and suppliers may move out, and new products are introduced or replacing existing ones; hence, the network structure is dynami- cally altering in terms of relations among nodes (arcs) which are mainly due to changes in preferences and performances over time. Such situations, i.e. the sheer number of participants and difficul- ties to rapidly identify suitable partners, reinforce the idea that the definition of information structure, the way we acquire and maintain the information, and the governing rules have critical roles in the success of the system (Cho, Mahdai, Mahdavi-Amiri, Mohebbi, & Zandakbari, 2011). In other words, while it is well- accepted by supply chain executives that information sharing can lead to enhanced supply chain performance (see La Londe & Ginter, 2004), the source, potential magnitude, and the allocation of the improvements across channel members are not clear (Sahina & Robinson, 2005). Today’s global e-marketplaces have changed their way of thinking to mitigate one of the most important failures of their ancestors: the ‘‘chicken and egg’’ problem. Buyers do not desire 0957-4174/$ - see front matter Ó 2012 Elsevier Ltd. All rights reserved. http://dx.doi.org/10.1016/j.eswa.2012.07.008 ⇑ Corresponding author. Address: Department of Industrial and Information Engineering, University of Tennessee, 408 East Stadium Hall, Knoxville, TN 37996- 0700, USA. Tel.: +1 865 974 7648; fax: +1 865 974 0588. E-mail addresses: mohebbi@utk.edu (S. Mohebbi), Xueping.Li@utk.edu (X. Li). Expert Systems with Applications 39 (2012) 13501–13508 Contents lists available at SciVerse ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa