Deliverables 2001, Quarter 3

Some papers may only be accessible by members of the Trade Agents project.

[1D2.2] Competitive Market-based Allocation of Consumer Attention Space: Concepts and Validation of Casy. (restricted access only)
The amount of attention space available for recommending suppliers to consumers on e-commerce sites is typically limited. We present a competitive distributed recommendation mechanism based on adaptive software agents for efficiently allocating the "consumer attention space", or banners. In the example of an electronic shopping mall, the task is delegated to the individual shops, each of which evaluates the information that is available about the consumer and his or her interests (e.g. keywords, product queries, and available parts of a profile). Shops make a monetary bid in an auction where a limited amount of "consumer attention space" for the arriving consumer is sold. Each shop is represented by a software agent that bids for each consumer. This allows shops to rapidly adapt their bidding strategy to focus on consumers interested in their offerings. For various basic and simple models for on-line consumers, shops, and profiles, we demonstrate the feasibility of our system by evolutionary simulations as in the field of agent-based computational economics (ACE). We also develop adaptive software agents that learn bidding-strategies, based on neural networks and strategy exploration heuristics. Furthermore, we address the commercial and technological advantages of this distributed market-based approach. The mechanisme we describe is not limited to the example of the electronic shopping mall, but can easily be extended to other domains.

[1D4.3] Business Case Demonstrator (restricted access only)
Technical report on further development of the demonstrators of 2000 for the business cases. One or both demonstrators will be extended with functionality and services to customers, shops, and mall, the results from the first half year on XML communication and the internal agent architecture will be integrated.

[1D4.4] Agent Modelling and Development Environment (restricted access only)
The evaluation of, and experimentation with, an (commercially) available agent modelling and development environment. Experiments will be set up to evaluate it with respect to the trade agent architecture, prototypes and conceptual framework of WU5.

[1D6.1] Implementation of a Competitive Market-Based Allocation of Consumer Attention Space (restricted access only)
In [Bohte et al.,2001] a competitive distributed recommendation mechanisme is introduced based on adaptive software agents for efficiently allocating the "consumer attention space", or banners. In the instance of an electronic shopping mall, the task of correctly profiling and analyzing the consumers is delegated to the individual shops that operate in a distributed, remote fashion. The evaluation and classification of consumers for the bidding on banners is not handled by a central agency as is customary, but is a distributed process where all shops bidding for a consumer partake. This allows each shop to apply its own private strategy, learning mechanisme and specific domain knowledge. Here we present a scalable, and extensible software agent architecture and prototype for distributed market-based allocation of consumer attention space. The prototype has an architecture suitable for supporting agents in a distributing bidding application where agents run on dedicated machines for maximum computational resources. Furthermore, as an extention, the agents can operate in multiple independent markets concurrently.