Evolving trading strategies using directional changes
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1435
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2016.12.032
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 145
- Volume
- 73
- Issue
- -
- ISSN
- 0957-4174
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
A - Artificial Intelligence (AI)
- Citation count
- 17
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes a novel trading strategy based on the concept of directional changes (DC) in asset pricing. Both the combination of multiple DC summaries, and the use of genetic algorithms to optimise evolution of multiple summaries, were unprecedented for creating profitable trading strategies, until this work. The strategy is validated over 255 datasets derived from high-frequency trading data. The results show this strategy is not only profitable, but statistically significantly outperforms classical trading approaches. The work influenced a step change in combining multiple summaries for maximum gain and minimal risk in financial trading strategies, rather than just single summaries.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -