Accession Number:

ADA461174

Title:

News and Trading Rules

Descriptive Note:

Doctoral thesis

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE

Personal Author(s):

Report Date:

2003-01-01

Pagination or Media Count:

213.0

Abstract:

AI has long been applied to the problem of predicting financial markets. While AI researchers see financial forecasting as a fascinating challenge, predicting markets has powerful implications for financial economics -- in particular the study of market efficiency. Recently economists have turned to AI for tools, using genetic algorithms to build trading strategies, and exploring the returns those strategies generate of evidence of market inefficiency. The primary aim of this thesis is to take this basic approach, and put the artificial intelligence techniques used on a firm footing, in two ways first, by adapting AI techniques to the stunning amount of noise in financial data second, by introducing a new source of data untapped by traditional forecasting methods news. I start with practitioner-developed technical analysis constructs, systematically examining their ability to generate trading rules profitable on a large universe of stocks. Then, I use these technical analysis constructs as the underlying representation for a simple trading rule learner, with close attention paid to limiting search and representation to fight overfitting. In addition, I explore the use of ensemble methods to improve performance. Finally, I introduce the use of textual data from internet message boards and news stories, studying their use both in isolation as well as augmenting numerical trading strategies.

Subject Categories:

  • Information Science
  • Economics and Cost Analysis
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE