Journal
DATA SCIENCE IN FINANCE AND ECONOMICS
Volume 2, Issue 2, Pages 96-116Publisher
AMER INST MATHEMATICAL SCIENCES-AIMS
DOI: 10.3934/DSFE.2022005
Keywords
investment strategy; economic forecasting; machine learning; pattern recognition; adaptive systems; stock markets; moving averages
Ask authors/readers for more resources
This article introduces an investment strategy based on the difference between two moving averages, allowing short-term prediction through pattern extraction, and uses machine learning to optimize strategy parameters. Satisfactory results were obtained in testing this strategy.
The article presents a certain investment strategy based on the difference between two moving averages, modified to allow the extraction of patterns. The strategy concept dropped the traditionally considered intersections of two averages and opening positions just after those intersections. Based on the observation of changes happening in the moving averages difference, it has been noticed that for some values of this difference and some values of additional strategy parameters, an interesting pattern appears that allows short-term prediction. These patterns also depended on the first derivative of the moving averages difference and the location of the current price relative to certain thresholds of the difference. Therefore, the strategy uses five parameters, including Stop Loss, adapted to the properties of the time series through machine learning. The importance of machine learning is highlighted by comparing simulation results with and without it. The strategy effectiveness was tested in the Matlab environment on the time series of the WIG20 (primary index of the Warsaw Stock Exchange) historical data. Satisfactory results were obtained considered in terms of minimizing investment risk measured by the Calmar indicator.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available