|Author:||Chan, Yau-choi Raymond|
|Title:||An agent-based information brokering system to bolster electronic commerce|
|Subject:||Hong Kong Polytechnic University -- Dissertations|
Department of Computing
|Pages:||xi, 95 leaves : ill. ; 30 cm|
|Abstract:||This research explores issues of engineering agents that partially automate some of the activities of information brokering in e-commerce. In particular, it focuses on addressing the problem of connecting buyers and sellers. An algorithm that uses multiple criteria to match buyers and sellers based on pre-specified user profiles was devised and implemented. The process of matching and connecting buyers and sellers are divided into four stages: selection, evaluation, filtering and assignment. Ideas of the approach of connection are realized in a testbed on securities trading consisting of a society of information agents (a broker agent, a recommendation agent and a record agent) and trading agents (buyer and seller agents) that communicate via a blackboard database. Buyer and seller agents send requests and advertisements to the testbed respectively to specify their preferences. The broker agent connects requests to advertisements based on factors like price, volume and utility of the trading agents. The broker agent determines how good each connection is and select the best to be recommended to the trading agents. Trading agents can then review connection results and choose to complete the deal. If matching trading partner cannot be found, the recommendation agent fries to identify potential buyers or sellers based on transaction histories kept locally by the record agent and send information to them via e-mails. In addition, an information brokering protocol was devised and implemented to structure the interactions and information exchange among agents in the testbed. A series of experiments that were carried out show favorable results in executing the protocol.|
Files in This Item:
|b15321459.pdf||For PolyU Staff & Students||3.28 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: