Abstract
The article presents a methodology for developing trading strategies based on genetic algorithms that use riskoriented metrics for optimization. Data from the Binance cryptocurrency exchange for 2021–2022 was used for development, and similar data for 2022–2024 was used for validation. The methodology was aimed to create the most effective combinations of two input and two output technical indicators. Based on the set of common indicators, all possible input and output signal combinations were generated, ensuring complete coverage of potential options. The total signal for each combination was calculated by summing the signals of individual indicators, which allowed determining the action (buy, hold, sell) at each moment based on the identified indicators. Several ratios (Sharpe, Sortino, Omega, maximum drawdown, and Calmar) assessed the effectiveness of each combination. These metrics allowed for a comprehensive analysis of profitability and risk for each trading strategy. Cases of extreme values were processed using quantiles. All coefficients were normalized using a min-max approach, which brought the data attributes to a standard scale. A genetic algorithm was used to identify the most effective combinations based on the generated evaluation function to optimize the weights. The population size of 8 provided sufficient genetic diversity, allowing the algorithm to explore and exploit the solution space efficiently. Crossover and mutation were used to explore new areas of the solution space, ensuring genetic diversity and preservation of successful traits. The results showed that the best 15 combinations of technical indicators showed an average profit of more than 50% on the validation sample. This indicates the effectiveness of the weights selected by the genetic algorithm when choosing combinations. The best combinations had the same output signals (TEMA+BB), which means their reliability, while the input signals were less stable but had leaders such as ICH and DC. The economic feasibility of the developed methodology is confirmed by high profitability, which is verified by historical data. The proposed approach can be effectively applied to create optimal trading strategies, ensuring high profitability and risk management.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
