Automated trading systems’ evaluation using d-Backtest PS method and WM ranking in financial markets
-
Author(s)Dimitrios VezerisLink to ORCID Index: https://orcid.org/0000-0002-2251-5772
,
Themistoklis Kyrgos
,
Ioannis Karkanis
,
Vasiliki Bizergianidou
-
DOIhttp://dx.doi.org/10.21511/imfi.17(2).2020.16
-
Article InfoVolume 17 2020, Issue #2, pp. 198-215
- Cited by
- 1056 Views
-
437 Downloads
This work is licensed under a
Creative Commons Attribution 4.0 International License
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.
Acknowledgments
We 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).
- Keywords
-
JEL Classification (Paper profile tab)F31, G17
-
References31
-
Tables8
-
Figures11
-
- Figure 1. Systems’ 3.5-year balance graph (January 2016 – July 2019) with compounding capital using the d-Backtest PS method for parameter selection
- Figure A1. EUR/USD chart with signals from the Ad1MA strategy
- Figure A2. EUR/USD chart with signals from the Ad2MA strategy
- Figure A3. EUR/USD chart with signals from the Ad3MA strategy
- Figure A4. EUR/USD chart with signals from the AdADX strategy
- Figure A5. EUR/USD chart with signals from the AdIchimoku strategy
- Figure A6. EUR/USD chart with signals from the AdMACD strategy
- Figure A7. EUR/USD chart with signals from the AdParSAR strategy
- Figure A8. EUR/USD chart with signals from the AdPivot strategy
- Figure A9. EUR/USD chart with signals from the AdTurtle strategy
- Figure A10. EUR/USD chart with signals from the AdBBAntiTrend strategy
-
- Table 1. Classification occurrences for all systems based on the WM values for d-Backtest PS method
- Table 2. Classification occurrences for all systems based on the WM values for best BTs
- Table 3. Classification occurrences for all systems based on the WM values for 6-month constant BT
- Table B1. Total results for Extended Profit Margin (xPM)
- Table B2. Total results for Sharpe ratio
- Table B3. Total results for Drawdown
- Table B4. Total results for Expected Payoff
- Table B5. Total results for Profit
-
- Appel, G. (2005). Technical Analysis: Power Tools for Active Investors. Upper Saddle River: FT Press.
- Azhikodan, A. R., Bhat, A. G. K., & Jadhav, M. V. (2019) Stock Trading Bot Using Deep Reinforcement Learning. In H. Saini, R. Sayal, A. Govardhan & R. Buyya (Eds.), Innovations in Computer Science and Engineering (pp. 41-29). Springer, Singapore.
- Bollinger, J. (2001). Bollinger on Bollinger Bands. New York City: McGraw-Hill.
- Booth, A., Gerding, E., & McGroarty, F. (2014). Automated trading with performance weighted random forests and seasonality. Expert Systems with Applications, 41(8), 3651-3661.
- Chong, T. T.-L., & Ng, W.-K. (2008). Technical analysis and the London stock exchange:testing the MACD and RSI rules using the FT30. Applied Economics Letters, 15(14), 1111-1114.
- Chou, Y.-H., Kuo, S.-Y., Chen, C.-Y., & Chao, H.-C. (2014). A Rule-Based Dynamic Decision-Making Stock Trading System Based on Quantum-Inspired Tabu Search Algorithm. IEEE Access, 2, 883-896.
- Curtis, F. (2007). Way of the Turtle: The Secret Methods that Turned Ordinary People into Legendary Traders. New York City: McGraw-Hill.
- Elliott, N. (2007). Ichimoku Charts: An introduction to Ichimoku Kinko Clouds. Hampshire, UK: Harriman House.
- Henrique, B. M., Sobreiro, V. A., & Kimura, H. (2018). Stock price prediction using support vector regression on daily and up to the minute prices. The Journal of Finance and Data Science, 4(3), 183-201.
- Ilić, V., & Brtka, V. (2011). Evaluation of algorithmic strategies for trading on foreign exchange market. Proceedings from Information and Communication Technologies for Small and Medium Enterprises. Arandjelovac, Serbia.
- Kim, H. S., Brorsen, B. W., & Anderson, K. B. (2010). Profit Margin Hedging. American Journal of Agricultural Economics, 92(3), 638-653.
- Kumiega, A., & Vliet, B. E. (2012). Automated Finance: The Assumptions andBehavioral Aspects of Algorithmic Trading. The Journal of Behavioral Finance, 51-55.
- Liu, Y., Yu, X., & Han, J. (2002). Sharpe Ratio-Oriented Active Trading:A Learning Approach. In Proceedings from Mexican International Conference on Artificial Intelligence (pp. 331-339). Mexico.
- Marcus, D. (2013). Portfolio Theory Forward Testing. Advances in Management & Applied Economics, 3(3), 225-244.
- Osunbor, V., & Egwali, A. (2016 ). Development of OSEG: A FOREX Expert Advisor. The Pacific Journal of Science and Technology, 17(2), 206-212.
- Pardo, R. (2012). The Evaluation and Optimization of Trading Strategies, Second Edition. Hoboken, New Jersey: John Wiley & Sons, Inc.
- Petropoulos, A., Chatzis, S., Siakoulis, V., & Vlachogiannakis, N. (2017). A stacked generalization system for automated FOREX portfolio trading. Expert Systems with Applications, 90, 290-302.
- Sharpe, W. (1975). Adjusting for Risk in Portfolio Performance Measurement. Journal of Portfolio Management, 1(2), 29-34.
- Silva, E., Castilho, D., Pereira, A. C., & Brandao, H. (2014). A neural network based approach to support the Market Making strategies in High-Frequency Trading. In Proceedings from International Joint Conference on Neural Networks (pp. 845-852). Beijing, China.
- Svoboda, J. (2012). 5 F performance indicator: A robust metric for trading systems evaluation? In Proceedings from: 1st WSEAS International Conference on Finance, Accounting and Auditing (FAA ’12) (p. 92). Zlin, Czech Republic: WSEAS Press.
- Trippi, R. R., & Desieno, D. (1991). Trading Equity Index Futures With A Neural Network. The Journal of Portfolio Management, 19(1), 27-33.
- Vezeris, D. T., & Schinas, C. J. (2018). Performance Comparison of Three Automated Trading Systems (MACD, PIVOT and SMA) by Means of the d-Backtest PS Implementation. International Journal of Trade, Economics and Finance, 9, 170-173.
- Vezeris, D. T., Kyrgos, T. S., & Schinas, A. C. (2018a). Hedging and non-hedging trading strategies on commodities using the d-Backtest PS method. Investment Management and Financial Innovations, 15, 351-369.
- Vezeris, D. T., Schinas, C. J., & Papaschinopoulos, G. (2016). Profitability Edge by Dynamic Back Testing Optimal Period Selection for Technical Parameters Optimization, in Trading Systems with Forecasting. Computational Economics, 51, 761-807.
- Vezeris, D., Karkanis, I., & Kyrgos, T. (2019). AdTurtle: An Advanced Turtle Trading System. Journal of Risk and Financial Management, 12, 96.
- Vezeris, D., Kyrgos, T., & Schinas, C. (2018b). Take Profit and Stop Loss Trading Strategies Comparison in Combination with an MACD Trading System. Journal of Risk and Financial Management, 11, 56.
- Wang, Y., Lee, H., Xiang, Y., Liu, Y., Lei, Z. B., & Chau, K. Y. (2019). Trading Strategies Evaluation Platform with Extensive Simulations. Proceedings from IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr). Shenzhen, China.
- Wilder, W. (1978). New Concepts in Technical Trading Systems. Greensboro, N.C: Trend Research.
- Wu, H.-C., Tseng, C.-M., Chan, P.-C., Huang, S.-F., Chu, W.-W., & Chen, Y.-F. (2012). Evaluation of stock trading performance of students using a web-based virtual stock trading system. Computers & Mathematics with Applications, 64(5), 1495-1505.
- Yao, S., Pasquier, M., & Quek, C. (2007). A foreign exchange portfolio management mechanism based on fuzzy neural networks. In Proceedings from IEEE Congress on Evolutionary Computation (pp. 2576-2583). Singapore.
- Yong, B. X., Rozaini, M., & Abdullah, A. S. (2017). A Stock Market Trading System Using Deep Neural Network. Proceedings from Asian Simulation Conference 2017. Melaka, Malaysia.
-
Dynamic relationship between equity, bond, commodity, forex and foreign institutional investments: Evidence from India
Rajeev Matha ,
Geetha E. ,
Satish Kumar ,
Raghavendra
doi: http://dx.doi.org/10.21511/imfi.19(4).2022.06
Investment Management and Financial Innovations Volume 19, 2022 Issue #4 pp. 65-82 Views: 808 Downloads: 184 TO CITE АНОТАЦІЯThe interrelationship between equity, bond, commodity and forex movements can provide investors with abundant trading opportunities regardless of whether one market is trending upward or downward. Hence, to understand the interlinkage between markets, this study examines the long-run and causal linkage between forex, G-sec bonds, oil prices, gold rates, foreign institutional investment (FII) flows, and equity market and sectoral index returns. Daily time-series data from August 2012 to August 2021 were considered for empirical analysis. Johansen’s cointegration test revealed that foreign exchanges like USD, Euro, GBP and Yen, oil and gold rates, G-bond returns and FII flows were significantly cointegrated with the stock market and sectoral indices in the long run. Further, Granger causality found a uni-directional relationship between forex rates (i.e., USD, Euro, Yen) and the market, as well as sectoral indices, except Nifty 50 and Nifty IT indices. Oil price movements were found to effectively predict future price changes of Nifty consumer durables, auto, IT indices. Gold prices are useful to predict Nifty-Auto, Bank, Financial Services, Oil & Gas and PSU. The study also found a bi-directional relationship from FII inflows to the stock market and sectoral indices. The findings suggest that forex rates, oil prices and FII flows significantly affect India’s stock market and sectoral performance. The study contributes to the existing literature by comprehensively examining the interlinkage between commodities such as oil and gold, foreign exchanges like USD, Euro, GBP and Yen, G-bond, FII flows and the stock market, and fourteen sectoral indices in the Indian context.
