Financial News Analysis for Intelligent Portfolio Management - Robotics Institute Carnegie Mellon University

Financial News Analysis for Intelligent Portfolio Management

Young-Woo Seo, Joseph Andrew Giampapa, and Katia Sycara
Tech. Report, CMU-RI-TR-04-04, Robotics Institute, Carnegie Mellon University, 2004

Abstract

In this paper, we present Warren, a multi-agent system for intelligent portfolio management, which is motivated by the great benefits of working in teams within the domain of Distributed Artificial Intelligence (DAI) and TextMiner which takes advantage of information retrieval techniques to complement quantitative financial information. In the portfolio management domain, software agents that evaluate the risks associated with the individual companies in a portfolio should be able to read news articles that indicate the financial outlook of a company. There is a positive correlation between news reports on a company's financial outlook and its attractiveness as an investment. Since it is impossible for financial analysts or investors to track and read each one, it would be very helpful to have a technology for automatically analyzing news reports that reflect positively or negatively on a company's financial outlook. It is also necessary for an agent to learn contextual changes in the news reports autonomously. To accomplish these tasks, we devised a new text classification method and a sampling method. With comprehensive quantitative information gathered by efficient coordinations between agents, and the supplementing of quantitative information by financial news analysis, we showed a successful application of a multi-agent system for portfolio management.

BibTeX

@techreport{Seo-2004-8841,
author = {Young-Woo Seo and Joseph Andrew Giampapa and Katia Sycara},
title = {Financial News Analysis for Intelligent Portfolio Management},
year = {2004},
month = {January},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-04-04},
keywords = {Intelligent Portfolio Management, Multi-Agents System, Machine Learning, Information Retrieval, Artificial Intelligence},
}