Clarification of a profitable trading system based on dynamic analysis

Subject Areas : Financial Engineering

Atefeh Bagheri Naghneh ¹ , Sayyed Mohammad Reza Davoodi ²

1 - Department of Industrial Engineering, Dehaghan Branch, Islamic Azad University, Dehaghan, Iran.
2 - Department of Management, Dehaghan Branch, Islamic Azad University, Dehaghan, Iran.

Received: 2021-12-14 Accepted : 2022-04-09 Published : 2022-05-22

Keywords: singular value decomposition, Dynamic system, dynamic mode decomposition, eigenvector and eigenvalue,

Abstract :

Purpose: The purpose of this study is to predict stock returns and ultimately present a trading strategy based on dynamic analysis.Methodology: The behavior of a stock portfolio can be considered as a complex and chaotic dynamic system in which the return of the portfolio is a state variable that reflects the state of the system. Dynamic mode decomposition is one of the methods in which with the help of available data, a linear approximation of the nonlinear operator governing the system is obtained and by calculating the main modes, the system output can be explicitly calculated in terms of time.Findings: The results of research on a portfolio consisting of 14 industries from the Tehran Stock Exchange in the period 2010 to 2019 and considering the 5 main modes of system guidance show that the optimal lag is six and the Sharp ratio obtained from the trading system of two Equivalent to the buy and hold system.Originality / Value: Therefore, the use of this trading system is recommended for short-term trading.

References:

دولو، مریم؛ مسکینی مود، شایان. (1398). بررسی عملکرد استراتژی معاملاتی مبتنی بر غلبه تصادفی. دانش مالی تحلیل اوراق بهادار، 12(41), 193-171.

رئوفی، علی؛ محمدی، تیمور. (1397). پیش‌بینی بازده بازار سهام تهران با استفاده از ترکیب تجزیه موجک و شبکه عصبی فازی تطبیقی. پژوهش‌های اقتصادی ایران، 23(76)، 136-107.

سارنج، علیرضا؛ قاسمی، احمدرضا؛ ارم، اصغر؛ تهرانی، رضا (1399). طراحی سیستم معاملاتی تکنیکی سهام با استفاده از مدل ترکیبی شبکه عصبی MLP و الگوریتم‌های تکاملی، دانش مالی تحلیل اوراق بهادار، 13(45)، 64-47.

فرخ، مجتبی. (1400). انتخاب سبد سهام فازی با بررسی هم‌زمان بازده و ریسک نامطلوب. پژوهش‌های نوین در تصمیم‌گیری، 6(2), 18-1.

فلاح‌پور، سعید؛ حکیمیان، حسن. (1398). بهینه‎سازی استراتژی معاملات زوجی با استفاده از روش یادگیری تقویتی، با به‌کارگیری دیتاهای درون‎روزی در بورس اوراق بهادار تهران. تحقیقات مالی، 1(21)،19-34.

لطیفی بنماران، معصومه؛ سعیدی، علی، (1397)، آزمون رویکرد دینامیک سیستم‌ها در شناسایی عوامل تأثیرگذار بر حباب قیمتی بورس اوراق بهادار تهران، کنگره ملی تحقیقات بنیادین در مدیریت اقتصاد و حسابداری، تهران.

یافتیان، امیرحسین؛ رستگار، محمدعلی. (1399). طراحی یک سیستم معاملاتی خودکار با استفاده از شبکه عصبی پیچشی. نشریه چشم‌انداز مدیریت مالی، 10(31), 184-153.

 

Awajan, A. M., Ismail, M. T., & Wadi, S. A. (2019). Stock market forecasting using empirical mode decomposition with holt-winter. Proceedings of the International Conference on Mathematical Sciences and Technology 2018 (MATHTECH2018): Innovative Technologies for Mathematics & Mathematics for Technological Innovation.

Capinski, M., & Zastawniak, T. (2003). Mathematics for finance : an introduction to financial engineering. Liangjing Publishing House.

Cui, L., & Long, W. (2016). Trading strategy based on dynamic mode decomposition: Tested in Chinese stock market. Physica A: Statistical Mechanics and Its Applications, 461, 498–508.

Davallou, M., Meskinimood, S. (2019). Performance examination of trading strategy based on Stochastic Dominance. Financial Knowledge of Securities Analysis, 12(41), 171-193. [In Persian]

Dori, D., Sillitto, H., Griego, R. M., McKinney, D., Arnold, E. P., Godfrey, P., Martin, J., Jackson, S., & Krob, D. (2020). System Definition, System Worldviews, and Systemness Characteristics. IEEE Systems Journal, 14(2), 1538–1548.

Fallahpour, S., Hakimian, H. (2019). Paired Trading Strategy Optimization Using the Reinforcement Learning Method: Intraday Data of Tehran Stock Exchange. Financial Research Journal, 21(1), 19-34. [In Persian]

Farrokh, M. (2021). Fuzzy Portfolio Selection Model by Considering the Return and Downside Risk. Modern Research in Decision Making, 6(2), 1-18. [In Persian]

Hua, J.-C., Roy, S., McCauley, J. L., & Gunaratne, G. H. (2016). Using dynamic mode decomposition to extract cyclic behavior in the stock market. Physica A: Statistical Mechanics and Its Applications, 448, 172–180.

Kuttichira, D. P., Gopalakrishnan, E. A., Menon, V. K., & Soman, K. P. (2017). Stock price prediction using dynamic mode decomposition. 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

Latifi Banmaran, M,. Saeedi, A. (2015), Testing the dynamics approach of systems in identifying the factors affecting the price bubble of Tehran Stock Exchange, National Congress of Fundamental Research in Management of Economics and Accounting, Tehran. [In Persian]

Lu, H., & Tartakovsky, D. M. (2020). Prediction Accuracy of Dynamic Mode Decomposition. SIAM Journal on Scientific Computing, 42(3), A1639–A1662.

Lynch, S. (2018). Dynamical Systems with Applications using Python. Springer International Publishing.

Mann, J., & Kutz, J. N. (2016). Dynamic mode decomposition for financial trading strategies. Quantitative Finance, 16(11), 1643–1655.

Manning, J., & Baldick, R. (2019). Forecasting short-term dynamics of shallow cumuli using dynamic mode decomposition. Journal of Renewable and Sustainable Energy, 11(5), 053704.

Meiss, J. D. (2007). Differential Dynamical Systems. Society for Industrial and Applied Mathematics.

Ramos, E. M., Darze, G. M., do Nascimento, F. R. T., Faccini, J. L. H., & Giraldi, G. A. (2020). Comparison of Dynamic Mode Decomposition and Deep Learning Techniques for Two-Phase Flows Analysis. Flow, Turbulence and Combustion, 105(4), 1345–1379.

Raoofi, A., Mohammadi, T. (2018). Forecasting Tehran Stock Exchange Index Returns Using a Combination of Wavelet Decomposition and Adaptive Neural Fuzzy Inference Systems. Iranian Journal of Economic Research, 23(76), 107-136. [In Persian]

Saranj, A., Ghasemi, A., Eram, A., Tehrani, R. (2020). Developing a Stock Technical Trading System Integrating MLP Neural Network with Evolutionary Algorithms. Financial Knowledge of Securities Analysis, 13(45), 47-64. [In Persian]

Schmidt, V. A. (2008). Discursive Institutionalism: The Explanatory Power of Ideas and Discourse. Annual Review of Political Science, 11(1), 303–326. ‌

Schneider, J. (2019). Was There a Precapitalist World-System? Core/Periphery Relations in Precapitalist Worlds, 45–66.

Yaftian, A., Rastegar, M. (2020). Designing an Automated Trading System Using Convolutional Neural Network. ـJournal of Financial Management Perspective, 10(31), 153-184. [In Persian]

Yin, T., Liu, C., Ding, F., Feng, Z., Yuan, B., & Zhang, N. (2022). Graph-based stock correlation and prediction for high-frequency trading systems. Pattern Recognition, 122, 108209.

Zhang, Y., Liu, W., & Yang, X. (2022). An automatic trading system for fuzzy portfolio optimization problem with sell orders. Expert Systems with Applications, 187, 115822.