Genetic algorithm search for predictive patterns in multidimensional time series

Polanski, Arnold (2011) Genetic algorithm search for predictive patterns in multidimensional time series. Complex Systems, 19 (3). pp. 195-209.

Full text not available from this repository. (Request a copy)

Abstract

Based on an algorithm for pattern matching in character strings, a pattern matching machine is implemented that searches for occurrences of patterns in multidimensional time series. Before the search process takes place, time series data is encoded in user-designed alphabets. The patterns, on the other hand, are formulated as regular expressions that are composed of letters from these alphabets and operators. Furthermore, a genetic algorithm is developed to breed patterns that maximize a user-defined fitness function. In an application to financial data, it is shown that patterns bred to predict high exchange rates volatility in training samples retain statistically significant predictive power in validation samples.

Item Type:	Article
Faculty \ School:	Faculty of Social Sciences > School of Economics
UEA Research Groups:	Faculty of Social Sciences > Research Groups > Economic Theory Faculty of Social Sciences > Research Groups > Applied Econometrics And Finance Faculty of Science > Research Groups > Statistics
Related URLs:	https://content.wolfram.com/uploads/site...
Depositing User:	Julie Frith
Date Deposited:	09 Feb 2012 10:33
Last Modified:	11 Mar 2025 13:31
URI:	https://ueaeprints.uea.ac.uk/id/eprint/36953
DOI:

Actions (login required)

View Item