|
Home
Synopsis
Research
Papers |
Development of experimental prototypes for several application
problems in e-trade situations
We investigate several types of application areas and examples,
and develop new concepts, practical experimental solutions and guidelines.
In the first year and part of the second year of this work
unit, several (future) electronic trade situations are considered
from the commercial and application perspective, and start-off development
cases are designed and executed, by first defining feasible transaction
and trade models for these trade agents applications and then developing
actual first experimental prototypes. Examples are auctions, adaptive profiling
systems, negotiations, dynamic pricing, and customer relations.
Subsequently, further, advanced applications (experimental
prototypes) are carried out and assessed, where results of other work units
are also used, and where applied research is carried out and further business-related
choices are made. Focus areas concern e.g. adaptive profiling, negotiation
and auctions, pricing, customer relations, matching and brokering. Especially,
application of appropriate types of adaptive agents and of agent architectures
are worked out, to serve as examples for actual application of such systems.
Ways of investigation are implementation and experimentation, application
and evaluation in practice, or computer simulation. This is partly done
by the business partners. The experimental prototypes are built in cooperation
with work unit 4: then work unit
6 takes care of the design and implementation of the learning c.q.
strategic behaviour of an agent, whereas work unit 4
takes care of the agent architecture and agent technology implementation.
Also, guidelines and hands-on experience knowledge are
developed for application of the results of the other work units (especially
1, 2
and 5) in practical application
areas.
-
Currently available deliverables
[0D6.1] Business
Case `Financial Information Brokerage', Part 1 (restricted
access only)
Technical report on the first sketches of the business
case of ING, concerning the final pilot cases for this year. (2000 Q1)
[0D6.2] Business
Scenario Electronic Shopping Mall, Part 1 (restricted
access only)
Technical report on the first sketches of the business
case of KPN, concerning the final pilot cases for this year. (2000 Q1)
[0D6.3] Business
Case `Financial Information Brokerage', Part 2 (restricted
access only)
Technical report on business cases of ING, concerning
the pilot cases that will be worked on in the remainder of this year; final
description of the pilot case, in mutual agreement and cooperation with
CWI and TNO. (2000 Q2)
[0D6.4] Business
Case Electronic Shopping Mall KPN Research, Part 2 (restricted
access only)
Technical report on business cases of KPN, concerning
the pilot cases that will be worked on in the remainder of this year; final
description of the pilot case, in mutual agreement and cooperation with
CWI and TNO. (2000 Q2)
[0D6.5] Dynamic
Pricing of News Items (restricted access only)
Scientific report on the first design, implementation,
and simulation of a dynamic pricing system for the ING case. The dynamic
pricing agent adjusts price schemes based on on-line trading information
(market response). The performance is evaluated by a simulation with simple
customer models. The report also describes how the software is incorporated
in the demonstrator. (2000 Q4)
[0D6.6] Business
Cases in the Trade Agents Project (restricted
access only)
A concise overview document with references to specific
technical documents, results, and aims for the business cases. (2000 Q4)
[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.
[2D6.1] Business Case 'Financial Information Brokerage'
[3D6.1] Business Case "Financial Information Brokerage".
|
