Using Messaging Structure to Evolve Agents Roles in Electronic Markets

Exogenous dynamics play a central role in survival and evolution of institutions. In this paper, we develop an approach to automate part of this evolution process for electronic market places which bring together many online buyers and suppliers. In particular, for a given market place, we focus on other market places doing similar business, as a form of exogenous evolutionary factor. Automatically tracking and analyzing how other market places do their business has a number of difficulties; for example, different electronic markets- with similar purpose- might use different names for similar agent roles and tasks. In this paper, we argue that low level analysis of sequences of messages exchanged between agents within e-markets is an effective mechanism in integrating similar roles specifications, independent of what names these roles – or even the messages themselves – may take. We focus on the structure of messages (message schemas), sequences of message schemas, sets of sequences of message schemas to compare and integrate roles. Using statistical analysis over such structures we bypass the difficult problem of identifying semantics of roles and exchanged messages through their human readable names (syntactic forms). To allow such low level analysis, different e-market specifications are expressed using the same language. Our language of choice is a recently developed multi agent systems specification language, Islander 2.0. We illustrate our approach with example specifications and institutions simulation traces.