بررسی عملکرد دو مدل پیش بینی قیمت سهام، مبتنی بر شبکه ی عصبی حافظه ی کوتاه مدت طولانی و با دو رویکرد متفاوت انتخاب ویژگی و تجزیه ی سری زمانی

نوع مقاله : پژوهشی

نویسندگان

گروه مدیریت سیستم و بهره‌وری، دانشکده‌ی مهندسی صنایع، دانشگاه تربیت مدرس، تهران، ایران.

چکیده

امروزه توسعه‌ی مدل­های پیش‌بینی  قیمت، با توجه به گسترش روزافزون بازارهای مالی،  اهمیت بسیاری دارد. در پژوهش حاضر، دو مدل از ترکیب الگوریتم ژنتیک و الگوریتم تجزیه‌ی حالت متغیر به‌صورت جداگانه با شبکه‌ی عصبی LSTM ارائه شده است. در رویکرد انتخاب ویژگی، الگوریتم ژنتیک از میان تمام ویژگی­های ورودی مدل، زیرمجموعه­ای از ویژگی­ها را انتخاب و شبکه‌ی عصبی LSTM، با استفاده از ویژگی­های منتخب، قیمت سهام را پیش‌بینی می‌کند. اما در رویکرد تجزیه‌ی سری زمانی، سری زمانی قیمت سهام به‌عنوان یگانه ورودی مدل توسط الگوریتم VMD تجزیه می‌شود و شبکه‌ی عصبی LSTM با پیش‌بینی  توابع تولیدشده و تجمیع نتایج، قیمت سهام را پیش‌بینی می‌کند. در پژوهش حاضر، قیمت 5 سهم  بورس نیویورک با دو مدل پیشنهادی، پیش‌بینی و عملکرد آن‌ها مقایسه شده است. نتایج تجربی، برتری مدل GA-LSTM را  نسبت به سایر مدل­های معیار نشان می­دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Investigating the Performance of Two Stock Price Forecasting Models, Based on a Long Short-Term Memory Neural Network and with Two Different Approaches of Feature Selection and Time Series Analysis

نویسندگان [English]

  • keyvan Haghighi Naeini
  • Mohammad Ali Rastegar
Department of Systems and Productivity Management, Faculty of Industrial Engineering, Tarbiat Modares University, Tehran, Iran.
چکیده [English]

In the financial literature, the capital market plays an essential role in economic growth through the financing of enterprises, the optimal allocation of resources, the improvement of liquidity of assets, the improvement of company management, and the increase of transparency in the economy. One of the most important challenges that shareholders always face in the market is to make the right decision and be in the right position with buying and selling stocks. Stock forecasting that predicts future stock movements and benefits shareholders has been an attractive research area for financial studies and researchers for the past. In this research, we present two models of neural networks that receive inputs and predict price and movement trends, and finally, the performance of these two models is compared. The data studied in this research includes the price data of the 5 largest shares of the New York market during the years 2000 to 2020, in which 80 percent of the initial samples are used as training data and the remaining 20 percent are used as test data.

In the proposed VMD-LSTM model, first, the stock price time series is decomposed using the variational mode decomposition algorithm (VMD) into the intrinsic mode functions (IMF), and then each of these IMFs is predicted by the LSTM model and After interpreting the results. In the second proposed method, available features, including price and some of the most important technical indicators, are used to predict stock prices. In the GA-LSTM model, the genetic algorithm is first used to select the best features from the entire set of features. Then, the time series of the stock closing price was predicted by an LSTM network using the selected features. The results of the research showed that because both models are very good in price prediction, the proposed GA-LSTM model, which is developed based on feature selection, has less error and more accurate performance.

کلیدواژه‌ها [English]

  • Stock price prediction
  • deep learning
  • genetic algorithm
  • feature selection
  • time series decomposition
1.  Berradi, Z., Lazaar, M., Mahboub, O. and Omara, H., 2021, June. A comprehensive review of artificial intelligence Techniques in Financial Market. In 2020 6th IEEE congress on information science and technology (CiSt), pp. 367-371. IEEE. https://doi.org/10.1109/CiSt49399.2021.9357175
2. Le, D.Y.N., Maag, A. and Senthilananthan, S., 2020, November. Analysing stock market trend prediction using machine & deep learning models: A comprehensive review. In 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), pp. 1-10. IEEE. https://doi.org/10.1109/CITISIA50690.2020.9371852
3. Arel, I., Rose, D.C. and Karnowski, T.P., 2010. Deep machine learning-a new frontier in artificial intelligence research [research frontier]. IEEE computational intelligence magazine5(4), pp.13-18. https://doi.org/10.1109/MCI.2010.938364
4. Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S. and Lew, M.S., 2016. Deep learning for visual understanding: A review. Neurocomputing187, pp.27-48. https://doi.org/10.1016/j.neucom.2015.09.116
5. LeCun, Y., Bengio, Y. and Hinton, G., 2015. Deep learning. nature521(7553), pp.436-444. https://doi.org/10.1038/nature14539
6. Adhikari, R. and Agrawal, R.K., 2014. A combination of artificial neural network and random walk models for financial time series forecasting. Neural Computing and Applications24, pp.1441-1449. https://doi.org/10.1007/s00521-013-1386-y
7. Niu, H. and Wang, J., 2014. Financial time series prediction by a random data-time effective RBF neural network. Soft computing18, pp.497-508. https://doi.org/10.1007/s00500-013-1070-2
8. Das, S.P., Achary, N.S. and Padhy, S., 2016. Novel hybrid SVM-TLBO forecasting model incorporating dimensionality reduction techniques. Applied Intelligence45, pp.1148-1165. https://doi.org/10.1007/s10489-016-0801-3
9. Guo, T., Xu, Z., Yao, X., Chen, H., Aberer, K. and Funaya, K., 2016, October. Robust online time series prediction with recurrent neural networks. In 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 816-825. Ieee. https://doi.org/10.1109/DSAA.2016.92
10. Ding, G. and Qin, L., 2020. Study on the prediction of stock price based on the associated network model of LSTM. International Journal of Machine Learning and Cybernetics11(6), pp.1307-1317. https://doi.org/10.1007/s13042-019-01041-1
11. Liu, Y., 2019. Novel volatility forecasting using deep learning–long short term memory recurrent neural networks. Expert Systems with Applications132, pp.99-109. https://doi.org/10.1016/j.eswa.2019.04.038
12. Zeng, X., Cai, J., Liang, C. and Yuan, C., 2022. A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. Plos one17(8), p.e0272637. https://doi.org/10.1371/journal.pone.0272637
13. Alotaibi, S.S., 2021. Ensemble technique with optimal feature selection for Saudi stock market prediction: a novel hybrid red deer-grey algorithm. IEEE Access9, pp.64929-64944. https://doi.org/10.1109/ACCESS.2021.3073507
14. Chung, H. and Shin, K.S., 2018. Genetic algorithm-optimized long short-term memory network for stock market prediction. Sustainability10(10), p.3765. https://doi.org/10.3390/su10103765
15. Niu, H., Xu, K. and Wang, W., 2020. A hybrid stock price index forecasting model based on variational mode decomposition and LSTM network. Applied Intelligence50, pp.4296-4309. https://doi.org/10.1007/s10489-020-01814-0
16. Qiu, J., Wang, B. and Zhou, C., 2020. Forecasting stock prices with long-short term memory neural network based on attention mechanism. PloS one15(1), p.e0227222. https://doi.org/10.1371/journal.pone.0227222
17. Ali, M., Khan, D.M., Alshanbari, H.M. and El-Bagoury, A.A.A.H., 2023. Prediction of complex stock market data using an improved hybrid emd-lstm model. Applied Sciences13(3), p.1429. https://doi.org/10.3390/app13031429
18. Chen, X., Cao, L., Cao, Z. and Zhang, H., 2024. A multi-feature stock price prediction model based on multi-feature calculation, LASSO feature selection, and Ca-LSTM network. Connection Science36(1), p.2286188. https://doi.org/10.1080/09540091.2023.2286188
19. Gülmez, B., 2023. Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm. Expert Systems with Applications227, p.120346. https://doi.org/10.1016/j.eswa.2023.120346
20. Nasiri, H. and Ebadzadeh, M.M., 2023. Multi-step-ahead stock price prediction using recurrent fuzzy neural network and variational mode decomposition. Applied Soft Computing148, p.110867. https://doi.org/10.1016/j.asoc.2023.110867
21. Mandic, D.P. and Chambers, J.A., 1999. Exploiting inherent relationships in RNN architectures. Neural networks12(10), pp.1341-1345. https://doi.org/10.1016/S0893-6080(99)00076-3
22. Wang, D., Fan, J., Fu, H. and Zhang, B., 2018. Research on optimization of big data construction engineering quality management based on RNN‐LSTM. complexity2018(1), p.9691868. https://doi.org/10.1155/2018/9691868
23. Katoch, S., Chauhan, S.S. and Kumar, V., 2021. A review on genetic algorithm: past, present, and future. Multimedia tools and applications80, pp.8091-8126. https://doi.org/10.1007/s11042-020-10139-6
24. Dragomiretskiy, K. and Zosso, D., 2013. Variational mode decomposition. IEEE transactions on signal processing62(3), pp.531-544. https://doi.org/10.1109/TSP.2013.2288675