Efficient agent-based negotiation for telecommunications services

We investigate the usage and functionality of an intelligent software agent negotiating for telecommunications services on behalf of the user. The objective of this agent is to select the best of the service combinations offered by multiple service retailers, taking into account both user preferences as encoded in the user profile and the corresponding charges given by the retailers. The agent analyzed is based on a simple yet informative model for on-line calculation of the utility of the user for the various service combinations, and on an algorithm for fast and efficient negotiation, which is not based on any assumptions regarding the structure of retailer tariffs. We assess our approach both analytically and experimentally, and we argue that the negotiation algorithm is either optimal or close to this for a variety of interesting cases. Although our approach is illustrated by dealing with a particular news-on-demand service, it is broadly applicable. We also argue that it pertains to both Internet and ATM network technologies