Automatic Trading Agent. RMT based Portfolio Theory and Portfolio Selection

Malgorzata Snarska and Jakub Krzych

Papers from arXiv.org

Abstract: Portfolio theory is a very powerful tool in the modern investment theory. It is helpful in estimating risk of an investor's portfolio, which arises from our lack of information, uncertainty and incomplete knowledge of reality, which forbids a perfect prediction of future price changes. Despite of many advantages this tool is not known and is not widely used among investors on Warsaw Stock Exchange. The main reason for abandoning this method is a high level of complexity and immense calculations. The aim of this paper is to introduce an automatic decision - making system, which allows a single investor to use such complex methods of Modern Portfolio Theory (MPT). The key tool in MPT is an analysis of an empirical covariance matrix. This matrix, obtained from historical data is biased by such a high amount of statistical uncertainty, that it can be seen as random. By bringing into practice the ideas of Random Matrix Theory (RMT), the noise is removed or significantly reduced, so the future risk and return are better estimated and controlled. This concepts are applied to the Warsaw Stock Exchange Simulator http://gra.onet.pl. The result of the simulation is 18 % level of gains in comparison for respective 10 % loss of the Warsaw Stock Exchange main index WIG.

Date: 2006-08
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Published in Acta Phys. Pol. B 37 (2006) 3145

Downloads: (external link)
http://arxiv.org/pdf/physics/0608293 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:physics/0608293

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().