Agent-mediated architecture for reputation-based electronic tourism systems: A neural network approach

Agent technology can be used in searching and selecting a good e-tourism system. However, most such systems focus mainly on price and avoid important purchasing decision-making factors such as quality and reputation. Here we define a reputation-based architecture for an e-tourism system that we have called 'reputation-based electronic tourism' (RET). An artificial neural network model was created for a reputation agent to evaluate capabilities for selecting products and services in an e-tourism setting. The classification performance of the model was compared to another method. The results indicated that RET could outperform and be more accurate in classifying perspective products and services for consumers. (c) 2006 Elsevier B.V. All rights reserved.