Detecting Statistical Arbitrage Opportunities Using a Combined Neural Network - GARCH Model

14 Pages Posted: 15 Jan 2012 Last revised: 24 Jan 2012

See all articles by Nikolaos S. Thomaidis

Nikolaos S. Thomaidis

University of the Aegean - Department of Financial Engineering & Management - Decision & Management Engineering Laboratory

Nick Kondakis

NGSQ International, Ltd

Date Written: January 12, 2012

Abstract

This paper proposes a hybrid computational intelligent system for the detection of statistical arbitrage opportunities in pairs of assets. The proposed methodology combines nonlinear neural network autoregressive models with GARCH parametrizations of volatility for describing the dynamics of the correction of relative mispricings. First results from this approach seem encouraging; further experimentation on the optimal sampling frequency, the forecasting horizon and the points of entry and exit is conducted, in order to improve the economic value when transaction costs are taken into account.

Suggested Citation

Thomaidis, Nikolaos S. and Kondakis, Nicholas, Detecting Statistical Arbitrage Opportunities Using a Combined Neural Network - GARCH Model (January 12, 2012). Available at SSRN: https://ssrn.com/abstract=1984252 or http://dx.doi.org/10.2139/ssrn.1984252

Nikolaos S. Thomaidis (Contact Author)

University of the Aegean - Department of Financial Engineering & Management - Decision & Management Engineering Laboratory ( email )

8 Michalon Str
Chios, GR 82 100
Greece
30-2271-0-35454 (Phone)
30-2271-0-35499 (Fax)

HOME PAGE: http://decision.fme.aegean.gr

Nicholas Kondakis

NGSQ International, Ltd ( email )

Hauppauge, NY
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
977
Abstract Views
3,235
Rank
43,480
PlumX Metrics