Genetic Algorithm for Pairs Trading

We have discussed previously how a complex trading system can be profitable. In a similar context, Reference [1] applied a genetic algorithm to pairs trading. The authors developed a sophisticated genetic optimization algorithm that utilizes Bollinger Bands and correlation-coefficient for pairs trading The algorithm encoded six important variables into a chromosome: the correlation coefficient threshold, the Bollinger Band entry width, the Bollinger Bands exit width, the correlation coefficient calculation days, the moving average calculation days, and the forward observation days. The encoded parameters are utilized to examine the trading pairs and their trading signals produced by the Bollinger Bands, after which the fitness value is calculated by averaging the return and volatility of long and short trading pairs. The genetic procedure was repeated until suitable parameters are discovered. After performing numerical experiments, the authors concluded,

Trading strategies are commonly used approaches for finding buying or selling signals for trading. One type of trading strategy is the pairs trading strategy. In the past, parameters in pairs trading strategies are usually set through experience, which is typically time-consuming. In this paper, negative correlation coefficient trading pairs, genetic algorithms, and Bollinger Bands are considered in AGBCPT, the proposed advanced genetic Bollinger Bands and correlation-coefficient based pairs trading algorithm, to determine the appropriate parameters for the long-short pairs trading strategy. To verify the effectiveness of AGBCPT, experiments were conducted on real datasets, showing that the parameters considered in pairs trading do affect the profitability of the pairs trading strategy; AGBCPT profit is superior to that of BAH and GBCPT for three stock market trends on various training and testing periods; and the fitness function used in AGBCPT also outperforms that of the previous approach in terms of reducing the trading risk of the trained model.

In short, the Genetic Algorithm-based pairs trading strategy produced better risk-adjusted returns. This article demonstrated once again that a complex trading system can be profitable with enough research and practice.

We believe that the key to developing a good trading system is thorough testing of its robustness, especially on out-of-sample data. What do you think? Let us know in the comments below.

References

[1] Chen C.-H., Lai W.-H., Hung S.-T., Hong, T.-P. , An Advanced Optimization Approach for Long-Short Pairs Trading Strategy Based on Correlation Coefficients and Bollinger Bands, Appl. Sci. 2022, 12, 1052. https://doi.org/10.3390/app12031052

Originally Published Here: Genetic Algorithm for Pairs Trading