مطالعه‌ای بر رفتار داده‌های بازده شاخص بورس تهران و ارائه روش پیش‌بینی تغییر رژیم مبتنی بر شبکه‌های عصبی عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مدیریت مالی، موسسه آموزش عالی ارشاد دماوند، تهران،‌ ایران.

2 استادیار، گروه مالی و بیمه، دانشگاه تهران، تهران، ‌ایران.

3 استادیار، گروه حسابداری، دانشگاه الزهراء، تهران، ‌ایران.

چکیده

در‌این پژوهش با نگاهی آماری بر داده‌های بورس تهران اقدام به شناسایی رفتار و فرآیند تولید داده‌های بازده روزانه شاخص بورس تهران شده و پس از انجام آزمون‌های متعدد، با شناسایی رفتار آماری‌این داده‌ها و اظهارنظر راجع به کارایی‌این بازار، اقدام به توسعه مدلی نوین برای پیش‌بینی  آن شده است. لازم به ذکر است که ساختار مدل ارائه شده مطابق با رفتار آماری‌این داده‌ها تدوین شده است. مدل ارائه‌شده متشکل از دو شبکه عصبی مصنوعی احتمال ترکیبی و حافظه کوتاه‌مدت و بلندمدت ماندگار می‌باشد که با در نظر گرفتن تعداد رژیم‌های رفتاری متفاوت، حرکات روزانه بازده شاخص بورس تهران را در بازه زمانی آذر 1387 تا فروردین 1400 توضیح می‌دهد. آزمون‌های متفاوت کارایی ضعیف بازار را رد کرده و ذات آشوبی را در رفتار بازده شاخص کل بورس تهران نشان می‌دهد. مدل ارائه‌شده در‌این پژوهش توانسته است دقت بهتری نسبت به مدل بدون در نظر گرفتن رژیم کسب بنماید. آزمون دیابولد ماریانو معنی‌دار بودن‌این تفاوت دقت مدل‌ها را تائید کرده و آزمون معکوس با در نظر گرفتن هزینه معاملاتی نشان داده است که استراتژی‌این مدل با در نظر گرفتن چند رژیم، بازده بالاتری نسبت به مدل بدون رژیم و شاخص بازار کسب می‌کند.

کلیدواژه‌ها

عنوان مقاله [English]

A study on the characteristics of TSE index return data and introducing a regime switching prediction method based on neural networks

نویسندگان [English]

  • Amin Aminimehr 1
  • Saeed Bajalan 2
  • Hanieh Hekmat 3
1 Masters student in Financial Management, Ershad Damavand Higher Education Institute, Tehran, Iran.
2 Assistant prof, Department of Financial Management and Insurance, University of Tehran, Tehran, Iran.
3 Assistant prof, Department of Accounting, Al Zahra University, Tehran, Iran.
چکیده [English]

This research has aimed at studying the characteristics and data generation process of TSE index daily return. Applying various tests showed that return data of TSE index follows a chaotic and clustered behavior. Furthermore, beside the condition of efficiency in this market, a novel prediction method is developed. The method introduced in this paper is formed from two consecutive neural networks; a mixture density neural network and a Long short-term memory neural network. It is worthy of note that the proposed method is associated with the inferred statistical structure from the data.  The entire model is compiled in order to predict TSE index considering various number of regimes using daily data December 2008 up to April 2021. Results from various statistical tests rejected the weak form of efficiency and manifested a chaotic behavior in TSE index return. Furthermore, the developed prediction method gained higher accuracy than the same method without considering regimes. Results from Diebold-Mariano test significantly implied the differences of the accuracy between the models with regimes and without regimes. Finally, a back test by considering transaction cost showed that the strategy based on the predicted direction of the model with regimes gains higher return than market benchmark and the model without regimes.

کلیدواژه‌ها [English]

  • Return prediction
  • Deep neural network
  • Adaptive Market Hypothesis
  • Efficient Market Hypothesis
  • Regime switching model

مراجع

  1. Aminimehr, A., Raoofi, A., Aminimehr, A., & Aminimehr, A. (2020). The Role of Feature Engineering in Prediction of Tehran Stock Exchange Index Based on LSTM. Iranian Journal of Economic Studies, 9(2), 527-548.
  2. Assadi, G., Morshedi, F. (2019). Investigating the effect of Investor Sentiment on the stock price crash risk in Tehran Stock Exchange. ـJournal of Financial Management Perspective, 9(25), 9-30(in persian)
  3. Babajani, J., Taghva, M., Blue, G., & Abdollahi, M. (2019). Forecasting Stock Prices in Tehran Stock Exchange Using Recurrent Neural Network Optimized by Artificial Bee Colony Algorithm. Financial Management Strategy, 7(2), 195-228(in persian).
  4. badiei, h., Rezazadeh, R., & Mahmoudi, H. (2017). Forecasting Stock Price Trend by Artificial Neural Networks (Case Study: Isfahan Oil Refinery Company). FEJ, 8(31), 167-185(in persian).
  5. Bildirici, M., & Ersin, Ö. Ö. (2009). Improving forecasts of GARCH family models with the artificial neural networks: An application to the daily returns in Istanbul Stock Exchange. Expert Systems with Applications, 36(4), 7355-7362.
  6. Bildirici, M., & Ersin, Ö. (2014). Modeling Markov Switching ARMA-GARCH Neural Networks Models and an Application to Forecasting Stock Returns. The Scientific World Journal, 2014, 497941.
  7. Bildirici, M., & Ersin, Ö. (2016). Markov Switching Artificial Neural Networks for Modelling and Forecasting Volatility: An Application to Gold Market. Procedia Economics and Finance, 38, 106-121.
  8. Bishop, C. (1994). Mixture density networks.
  9. Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307-327.
  10. Broock, W. A., Scheinkman, J. A., Dechert, W. D., & LeBaron, B. (1996). A test for independence based on the correlation dimension. Econometric Reviews, 15(3), 197-235.
  11. Busse, J. A., & Clifton Green, T. (2002). Market efficiency in real time. Journal of Financial Economics, 65(3), 415-437.
  12. Dima, B., & Miloş, L. (2009). TESTING THE EFFICIENCY MARKET HYPOTHESIS FOR THE ROMANIAN STOCK MARKET. Annales Universitatis Apulensis Series Oeconomica, 1, 41-41.
  13. Doan, T., & Lo, A. (1988). Stock Market Prices do not Follow Random Walks: Evidence from a Simple Specification Test. Review of Financial Studies, 1, 41-66.
  14. Engle, R. F. (1982). Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50(4), 987-1007.
  15. Fama, E. F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383-417
  16. Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
  17. Hajizadeh, E., Seifi, A., Fazel Zarandi, M. H., & Turksen, I. B. (2012). A hybrid modeling approach for forecasting the volatility of S&P 500 index return. Expert Systems with Applications, 39(1), 431-436.
  18. Hamilton, J. D. (1988). Rational-expectations econometric analysis of changes in regime: An investigation of the term structure of interest rates. Journal of Economic Dynamics and Control, 12(2), 385-423.
  19. Haofei, Z., Guoping, X., Fangting, Y., & Han, Y. (2007). A neural network model based on the multi-stage optimization approach for short-term food price forecasting in China. Expert Systems with Applications, 33(2), 347-356.
  20. Hasannejad, M. (2018). Designing a Model for Projection of Tehran Exchange Return Employing Autoregressive Moving Average (ARMA) and Autoregressive Moving Average with External Inputs (ARMAX) Models and Assessing the Performance Thereof. ـJournal of Financial Management Perspective, 8(22), 135-158. (in persian)
  21. Hekmat, Hanieh; Rahmani, Ali; Mola Nazari, Mahnaz; Mosavi, Mir Hossein; Ghalibaf Asl, Hasan (2020). Static & Dynamic Models & Stock Market Efficiency Evaluation of T.S.E. Listed Companies’. Financial Research Journal, 22(4), 476-495. (in Persian)
  22. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
  23. Kim, H. Y., & Won, C. H. (2018). Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications, 103, 25-37
  24. Kristjanpoller R, W., & Hernández P, E. (2017). Volatility of main metals forecasted by a hybrid ANN-GARCH model with regressors. Expert Systems with Applications, 84, 290-300.
  25. Kristjanpoller, W., & Minutolo, M. (2015). Gold price volatility: A forecasting approach using the Artificial Neural Network–GARCH model. Expert Systems with Applications, 42.
  26. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
  27. Lo, A., & Management, S. (1989). Long-term memory in stock market prices.
  28. Lo, A. W. (2004). The Adaptive Markets Hypothesis. The Journal of Portfolio Management, 30(5), 15.
  29. Zolfaghari, M., Sahabi, B., & Bakhtyaran, M. j. (2020). Designing a Model for Forecasting the Stock Exchange Total Index Returns (Emphasizing on Combined Deep Learning Network Models and GARCH Family Models). FEJ, 11(42), 138-171. (in Persian)
  30. Mohamed, A., Jawadi, F., & Nguyen, D. (2010). The Dynamics of Emerging Stock Markets: Empirical assessments and implications.
  31. Ozbayoglu, A. M., Gudelek, M. U., & Sezer, O. B. (2020). Deep learning for financial applications: A survey. Applied Soft Computing, 93, 106384.
  32. Park, J.-I., Lee, D.-J., Song, C.-K., & Chun, M.-G. (2010). TAIFEX and KOSPI 200 forecasting based on two-factors high-order fuzzy time series and particle swarm optimization. Expert Systems with Applications, 37(2), 959-967.
  33. Pele, D. T., & Voineagu, V. (2008). Testing market efficiency via decomposition of stock return. Application to Romanian Capital Market. Journal for Economic Forecasting, 5, 63-79.
  34. Pesaran, M. H., & Timmermann, A. (1992). A Simple Nonparametric Test of Predictive Performance. Journal of Business & Economic Statistics, 10(4), 461-465.
  35. Quandt, R. E. (1972). A New Approach to Estimating Switching Regressions. Journal of the American Statistical Association, 67(338), 306-310.
  36. Rather, A. M., Agarwal, A., & Sastry, V. N. (2015). Recurrent neural network and a hybrid model for prediction of stock returns. Expert Systems with Applications, 42(6), 3234-3241.
  37. Rosenberg, B., Reid, K., & Lanstein, R. (1985). Persuasive evidence of market inefficiency. The Journal of Portfolio Management, 11(3), 9.
  38. Samuelson, P. A. (2013). Proof that Properly Anticipated Prices Fluctuate Randomly. In the World Scientific Handbook of Futures Markets. Volume 5, pp. 25-38. WORLD SCIENTIFIC.
  39. Shiller, R. J. (1981). Do Stock Prices Move Too Much to be Justified by Subsequent Changes in Dividends? The American Economic Review, 71(3), 421-436.
  40. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15, 1929-1958.
  41. Ta, V.-D., Liu, C.-M., & Tadesse, D. A. (2020). Portfolio Optimization-Based Stock Prediction Using Long-Short Term Memory Network in Quantitative Trading. Applied Sciences, 10(2), 437.
  42. Tehrani, r., Tajdini, s., Abbasian, E., & Mirlohi, M. (2021). Measure the level of adherence to the random walk Theory in Various Industry Indices Using Markov Switching Model. Financial Management Strategy, 9(1). (in Persian)
  43. Vukovic, D., Vyklyuk, Y., Chernova, N., & Maiti, M. (2019). Neural network forecasting in prediction Sharpe ratio: Evidence from EU debt market. Physica A: Statistical Mechanics and its Applications, 542.
  44. Wang, W., Li, W., Zhang, N., & Liu, K. (2020). Portfolio formation with preselection using deep learning from long-term financial data. Expert Systems with Applications, 143, 113042.
  45. Wang, Y.-H. (2009). Nonlinear neural network forecasting model for stock index option price: Hybrid GJR–GARCH approach. Expert Systems with Applications, 36(1), 564-570.
  46. Zhong, X., & Enke, D. (2019). Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financial Innovation, 5(1), 24.
چشم انداز مدیریت مالی
دوره 11، شماره 34
شهریور 1400
صفحه 145-171

فایل ها

هم رسانی

ارجاع به این مقاله

آمار