Journal
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
Volume -, Issue -, Pages -Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s12652-020-02825-y
Keywords
Opening range breakout; Particle swarm optimization; Multi-objective optimization; Soft computing; Artificial intelligence
Ask authors/readers for more resources
This study proposes a scalable and continuous optimization algorithm for the Opening Range Breakout (ORB) trading strategy, referred to as PORB, and also introduces a multi-objective optimization algorithm, referred to as MPORB. Experimental results show that PORB significantly outperforms benchmark strategies in trading performance and time efficiency, while MPORB performs similarly to PORB but falls short in some cases. Overall, the PORB strategy overcomes limitations of previous solutions and the Pareto multi-objective optimization enhances trading performance without increasing time complexity.
Opening range breakout (ORB) is a well-known trading strategy in which predetermined price thresholds are used to characterize price movements. However, some researchers have noted that ORB does not make full use of market characteristics and fails to define a cogent closing strategy. Several modified ORB strategies have been optimized using grid-wise algorithms; however, those methods operate within a discrete limited solution space. In this study, we use the particle swarm optimization algorithm to create a scalable and continuous optimization algorithm, referred to as PORB. We also adopt the Pareto optimal in the creation of a multi-objective optimization algorithm, referred to as MPORB. Experiment results demonstrate that PORB significantly outperformed the benchmark strategies (GAORB and the original ORB) in trading performance and time efficiency. A PORB with stop-loss closing strategy slightly improves profitability and greatly reduces the risk of drawdown. The performance of MPORB is similar to that of PORB; however, in some cases it falls somewhat short. Overall, the scalable and continuous PORB strategy proposed in this study is shown to overcome the limitations of previous solutions. The implementation of Pareto multi-objective optimization in PORB is shown to enhance trading performance without increasing time complexity.
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