Automated trading systems’ evaluation using d-Backtest PS method and WM ranking in financial markets

Abstract

Given the popularity and propagation of automated trading systems in financial markets among institutional and individual traders in recent decades, this work attempts to compare and evaluate such ten systems based on different popular technical indicators in combination – for the first time – with the d-Backtest PS method for parameter selection. The systems use the technical indicators of Moving Averages (MA), Average Directional Index (ADX), Ichimoku Kinko Hyo, Moving Average Convergence/Divergence (MACD), Parabolic Stop and Reverse (SAR), Pivot, Turtle and Bollinger Bands (BB), and are enhanced by Stop Loss Strategies based on the Average True Range (ATR) indicator. Improvements in the speed of the back-testing computations used by the d-Backtest PS method over weekly intervals allowed examining all systems on a 3.5 years trading period for 7 assets in financial markets, namely EUR/USD, GBP/USD, USD/JPY, USD/CHF, XAU/USD, WTI, and BTC/USD. To evaluate the systems more holistically, a weighted metric is introduced and examined, which, apart from profit, takes into account more factors after normalization like the Sharpe Ratio, the Maximum Drawdown and the Expected Payoff, as well as a newly introduced Extended Profit Margin factor. Among the automated systems examined and evaluated using the weighted metric, the Adaptive Double Moving Average (Ad2MA) system stands out, followed by the Adaptive Pivot (AdPivot), and the Adaptive Average Directional Index (AdADX) systems. AcknowledgmentsWe would like to thank Dr. Christos Schinas for his time and invaluable guidance towards the methodology of the weighted metric. We would also like to thank Michalis Foulos for the hardware setup and support and Nektarios Mitakidis for his contribution to the representation of the results.This research has been co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH – CREATE – INNOVATE (project code: T1EDK-02342).

Untitled

“…Price forecasts are short-term profitable [8], but trend forecasts are long-term effective. Price forecasting systems use machine learning on time-series data [9], while trend forecasting systems use technical analysis indices. Price forecasting can improve trading outcomes, but price prediction is challenging [2].…”

Aplicação de Algoritmos de Otimização para a Minimização do Risco em um Portfólio de Negociações Automatizadas

“…Por outro lado existem portfólios que não utilizam quaisquer meios de otimizac ¸ão para distribuic ¸ão dinâmica do capital, tendo sido construídos simplesmente com a combinac ¸ão de diversos ATS atuando em um mesmo mercado. Estes sistemas estão sujeitos a prolongados períodos de drawdown (reduc ¸ão de capital) e estudos tem sido feitos sobre como controlar esse risco [Maier-Paape 2018, Vezeris et al 2020]. Nestes casos, através de otimizac ¸ões seria possível melhorar o rendimento e/ou diminuir o risco destes portfólios através de um rebalanceamento do posicionamento do capital dentre os ATS do portfólio.…”