Using KADS to Design a Multi-Agent Framework for Stock Trading

Short Description
Agent System for Stock Trading (MASST). The key issues it addresses include gathering and …… http://logic.stanford.edu/kif/Hypertext/kif-manual.html. …

Website: www2.dcs.hull.ac.uk | Filesize: 94kb

Content
Using KADS to Design a Multi-Agent Framework for Stock Trading
Darryl N. Davis and Yuan Luo
Neural, Emergent and Agent Technologies Group,
Department of Computer Science, University of Hull, HU6 7RX, UK
d.n.davis@dcs.hull.ac.uk
Abstract: A requirement analysis for a portfolio management in stock trading is presented. This
provides a theoretical foundation for a stock trading system. The overall portfolio management tasks
include eliciting user profiles, collecting information on the user’s initial portfolio position,
monitoring the environment on behalf of the user, and making decision suggestions to meet the user’s
investment goals. Based on the requirement analysis, this paper presents a framework for a Multi-
Agent System for Stock Trading (MASST). The key issues it addresses include gathering and
integrating diverse information sources with collaborating agents, and providing decision-making for
investors in the stock market. We identify the candidate agents and the tasks that the agents perform.
A KADS-based analysis of the processes within the framework is described in this paper.
Keywords: Multi-agent system, Knowledge-based system, Stock trading, Decision-making, KADS.1 Introduction
The stock market is one of the most popular investing places because of its expected high profit. The Internet, Web,
and other information technologies have brought and will continue to have a dramatic effect on the stock market.
Various types of financial information and stock trading have become available to investors from the Internet.
However, the information available from the Internet is disorganised and distributed over many server sites. The
variety of data sources is increasing dramatically and constantly changing. Therefore, information becomes
increasingly difficult for an individual investor to collect, filter, evaluate, and use for decision-making in stock
trading. As a result, the problem of locating and accessing information sources and filtering and integrating
information in support of decision making has become a critical task.
In their analysis of the portfolio management domain, Decker et al. (1996) point out that the fundamental task is
that of providing an integrated financial picture for the management of an investment portfolio over time, using the
information resources already available over the Internet. Central to this task is the provision of the best possible
rate of return for a specified level of risk, or conversely, to achieve a specified…