An Empirical Analysis of Stock Price Prediction Using Deep Learning Methods: LSTM, GRU, GAN, and WGAN-GP

Abstract

Financial markets are essential due to constantly changing economic conditions and global interactions. This study aims to accurately predict stock prices, which is crucial for investors and financial analysts. Conducting an empirical analysis using deep learning methods such as LSTM, GRU, GAN, and WGAN-GP, this research evaluates their performances and limitations, determining their applicability in financial forecasting by comparing them with existing literature. Utilizing Google stock data, LSTM demonstrates the best performance, followed by GAN. GRU performs better than WGAN-GP but falls behind LSTM and GAN. Unexpected events, notably the COVID-19 pandemic, result in significant gaps in these models' predictions. LSTM and GAN models prove applicable for short- and medium-term forecasts, emphasizing the necessity of enhancing sensitivity to unforeseen events. Future studies should delve into broader datasets and different markets, conduct sensitivity analyses, and optimize hyperparameters. Integrating fundamental and technical analysis data, macroeconomic factors, and market sensitivity analyses into deep learning models is crucial for future research. In this way, it is aimed to contribute to future studies to develop more effective and reliable financial forecasting models.

Keywords

• LSTM
• GRU
• GAN
• WGAN-GP
• Stock Price Prediction

Derin Öğrenme Yöntemleri Kullanılarak Hisse Senedi Fiyat Tahmini Üzerine Ampirik Bir Analiz: LSTM, GRU, GAN ve WGAN-GP

Abstract

Finansal piyasalar, sürekli değişen ekonomik koşullar ve küresel etkileşimler nedeniyle büyük öneme sahiptir. Bu çalışma, yatırımcılar ve finansal analistler için kritik olan hisse senedi fiyatlarını doğru tahmin etmeyi amaçlamaktadır. LSTM, GRU, GAN ve WGAN-GP gibi derin öğrenme yöntemleri kullanılarak yapılan ampirik analiz, bu yöntemlerin performanslarını ve sınırlılıklarını değerlendirmeyi, mevcut literatürle karşılaştırarak finansal tahminlerdeki uygulanabilirliklerini belirlemeyi hedeflemektedir. Google hisse senedi verileri kullanılarak yapılan çalışmada, LSTM'nin en iyi performansı gösterdiği, GAN'ın ikinci en iyi performansı sergilediği tespit edilmiştir. GRU, LSTM ve GAN'dan sonra performans gösterirken, WGAN-GP en düşük performansı göstermiştir. Beklenmedik olaylar, özellikle COVID-19 salgını, bu modellerin tahminlerinde belirgin sapmalara yol açmıştır. Sonuç olarak, LSTM ve GAN modellerinin kısa ve orta vadeli tahminler için uygulanabilir olduğu belirlenmiştir. Ancak, beklenmedik olaylara karşı duyarlılık geliştirme gerekliliği vurgulanmıştır. Gelecek çalışmaların daha geniş veri kümeleri ve farklı piyasalar üzerinde derinleşmesi, duyarlılık analizi ve hiperparametre optimizasyonunun yapılması önerilmektedir. Temel ve teknik analiz verilerinin, makroekonomik faktörlerin ve piyasa duyarlılık analizlerinin derin öğrenme modellerine entegrasyonunun önemi vurgulanmıştır. Bu şekilde, gelecekteki çalışmaların daha etkili ve güvenilir finansal tahmin modelleri geliştirmesine katkıda bulunulması hedeflenmektedir.

Keywords

• LSTM
• GRU
• GAN
• WGAN-GP
• Hisse Senedi Fiyat Tahmini

References

1. [1] P. J. Brockwell, R. A. Davis, Time Series: Theory and Methods, Springer Science & Business Media, New York, USA, 2013.
2. [2] J. D. Hamilton, Time Series Analysis, Vol. 2, Princeton University Press, Princeton, USA, 1994.
3. [3] R. H. Shumway, D. S. Stoffer, Time Series Analysis and Its Applications, Springer, New York, USA, 2011.
4. [4] X. Zhou, Z. Pan, G. Hu, S. Tang, and C. Zhao, "Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets," Mathematical Problems in Engineering, vol. 2018. pp. 1–11, 2018. doi:10.1155/2018/4907423
5. [5] Y. Kara, M. A. Boyacioglu, and Ö. K. Baykan, "Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange," Expert Systems with Applications, vol. 38, no. 5, pp. 5311-5319, May 2011. doi:10.1016/j.eswa.2010.10.027
6. [6] K. Karagül, "İstanbul Menkul Kıymetler Borsası'nda İşlem Gören Firmaların Destek Vektör Makineleri Kullanılarak Sınıflandırılması," Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, vol. 20, no. 5, ss. 174-178, 2014. doi:10.5505/pajes.2014.63835
7. [7] R. S. Latha, G. R. Sreekanth, R. C. Suganthe, M. Geetha, R. E. Selvaraj, S. Balaji, K. R. Harini, and P. P. Ponnusamy, "Stock Movement Prediction using KNN Machine Learning Algorithm," in Proceedings of the 2022 Int. Conf. on Computational Intelligence and Communication Networks (CICN), Mar. 15-17, 2022, Online [Online]. Available: IEEE Xplore. [Accessed: Mar. 9, 2023]. doi:10.1109/iccci54379.2022.9740781
8. [8] G. Kemalbay and B. N. Alkış, "Borsa endeks hareket yönünün çoklu lojistik regresyon ve k-en yakın komşu algoritması ile tahmini," Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, vol. 27, no. 4, pp. 556-569, 2021.

9. [9] S. Madge and S. Bhatt, "Predicting Stock Price Direction using Support Vector Machines," Independent Work Report, vol. 45, 2015.
10. [10] K. Khare, O. Darekar, P. Gupta, and V. Z. Attar, "Short term stock price prediction using deep learning," in Proceedings of the 2nd IEEE Int. Conf. on Recent Trends in Electronics, Information & Communication Technology (RTEICT), May 19-20, 2017, Bangalore, India [Online]. Available: IEEE Xplore. [Accessed: Mar. 9, 2023].
11. [11] S. Selvin, R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon, and K. P. Soman, "Stock price prediction using LSTM, RNN and CNN-sliding window model," in Proceedings of the Int. Conf. on Advances in Computing, Communications and Informatics (ICACCI), Sept. 13-16, 2017, Udupi, India [Online]. Available: IEEE Xplore. [Accessed: Mar. 9, 2023].
12. [12] L. Ji, Y. Zou, K. He, and B. Zhu, "Carbon futures price forecasting based with ARIMA-CNN-LSTM model," Procedia Computer Science, vol. 162, pp. 33-38, 2019.
13. [13] R. Alberto and C. Romero, "Generative Adversarial Network for Stock Market price Prediction," Unpublished report, Stanford University, San Francisco, USA, 2019.
14. [14] K. Zhang, G. Zhong, J. Dong, S. Wang, and Y. Wang, "Stock Market Prediction Based on Generative Adversarial Network," Procedia Computer Science, vol. 147, pp. 400-406, 2019.
15. [15] H. Raşo and M. Demirci, "Predicting the Turkish Stock Market BIST 30 Index using Deep Learning," Uluslararası Muhendislik Arastirma ve Gelistirme Dergisi, pp. 253–265, 2019. doi:10.29137/umagd.425560.
16. [16] V. D. Ta, C. M. Liu, and D. A. Tadesse, "Portfolio Optimization-Based Stock Prediction Using Long-Short Term Memory Network in Quantitative Trading," Applied Sciences, vol. 10, no. 2, p. 437, 2020.
17. [17] W. Lu, J. Li, Y. Li, A. Sun, and J. Wang, "A CNN-LSTM-Based Model to Forecast Stock Prices, "Complexity, vol. 2020, no. 1, pp. 1-10, 2020.
18. [18] C. Yang, J. Zhai, and G. Tao, "Deep Learning for Price Movement Prediction Using Convolutional Neural Network and Long Short-Term Memory, "Mathematical Problems in Engineering, pp. 1-13, 2020.
19. [19] R. Chandra and Y. He, "Bayesian neural networks for stock price forecasting before and during COVID-19 pandemic, "Plos One, vol. 16, no. 7, pp. 1-25, 2021.
20. [20] U. Demirel, H. Çam, and R. Ünlü, "Predicting Stock Prices Using Machine Learning Methods and Deep Learning Algorithms: The Sample of the Istanbul Stock Exchange," Gazi University Journal of Science, vol. 34, no. 1, pp. 63–82, 2021. doi:10.35378/gujs.679103
21. [21] N. Jing, Q. Liu, and H. Wang, "Stock price prediction based on stock price synchronicity and deep learning, "International Journal of Financial Engineering, vol. 8, no. 2, 2021.
22. [22] X. Yan, W. Weihan, and M. Chang, "Research on financial assets transaction prediction model based on LSTM neural network," Neural Computing and Applications, vol. 33, no. 1, pp. 257-270, 2021.
23. [23] H. Lin, C. Chen, G. Huang, and A. Jafari, "Stock price prediction using Generative Adversarial Networks, "Journal of Computer Science, vol. 17, no. 3, pp. 188-196, 2021.
24. [24] T. T. H. Giang, T. T. Nguyen, and Q. T. Le, "Dynamic Sliding Window and Neighborhood LSTM-Based Model for Stock Price Prediction, "SN Computer Science, vol. 3, no. 3, 2022.
25. [25] F. Han, X. Ma, and J. Zhang, "Simulating Multi-Asset Classes Prices Using Wasserstein Generative Adversarial Network: A Study of Stocks, Futures and Cryptocurrency, "Journal of Risk and Financial Management, vol. 15, no. 1, p. 26, 2022.
26. [26] H. Liu, L. Qi, and M. Sun, "Short-Term Stock Price Prediction Based on CAE-LSTM Method, "Wireless Communications and Mobile Computing, vol. 2022, no. 1, pp. 1-7, 2022.
27. [27] E. Albayrak ve N. Saran, “İstatistiksel ve Derin Öğrenme Modellerini Kullanarak Hisse Senedi Fiyat Tahmini,” Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, no. 16, vol. 2, pp. 161–169, 2023. doi:10.54525/tbbmd.1031017
28. [28] Ç. Çoban ve E. Hayat, “Hisse Senedi Piyasası Analizinde Farklı Derin Sinir Ağı Modellerinin Karşılaştırılması,” Adnan Menderes Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, no. 10, vol. 2, pp. 120–139, 2023. doi:10.30803/adusobed.1402228
29. [29] İ. Dalkıran ve M. Ozan, "Derin Öğrenme Teknikleri Kullanılarak Borsadaki Hisse Değerlerinin Tahmin Edilmesi," Avrupa Bilim ve Teknoloji Dergisi, no. 39, oo. 143-148, 2022. doi:10.31590/ejosat.1145949
30. [30] C. Erden, "Derin Öğrenme ve ARIMA Yöntemlerinin Tahmin Performanslarının Kıyaslanması: Bir Borsa İstanbul Hissesi Örneği," Yönetim ve Ekonomi Dergisi, no. 30, vol. 3, pp. 419-438, 2023. doi:10.18657/yonveek.1208807
31. [31] R. Mo, "Review of neural network algorithm and its application in reactive distillation, "Asian Journal of Chemical Sciences, vol. 9, no. 3, pp. 20-29, 2021. doi:10.9734/ajocs/2021/v9i319073
32. [32] K. Saini, N. Kumar, B. Bhushan, and R. Kumar, "Nonlinear complex dynamic system identification based on a novel recurrent neural network, "Springer Nature, vol. 1, no. 1, 2023. doi:10.21203/rs.3.rs-2894875/v1
33. [33] M. Safdar, "Feasibility of wildlife conservation based on artificial neural network," Nature Environmental Protection, vol. 1, no. 3, 2020. doi:10.38007/nep.2020.010304
34. [34] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.
35. [35] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
36. [36] J. Schmidhuber, "Deep learning in neural networks: An overview, "Neural Networks, vol. 61, pp. 85-117, 2015.
37. [37] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, no. 6088, pp. 533-536, 1986.
38. [38] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, and M. Wicke, "TensorFlow: A System for Large-Scale Machine Learning," in Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16), Nov. 2-4, 2016, Savannah, GA, USA [Online]. Available: USENIX. [Accessed: Mar. 10, 2023].
39. [39] F. Chollet, "Keras," Available: https://github.com/fchollet/keras [Accessed: May 10, 2023].
40. [40] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, "PyTorch: An imperative style, high-performance deep learning library, "Advances in Neural Information Processing Systems, vol. 8026-8037, 2019.
41. [41] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, "Caffe: Convolutional architecture for fast feature embedding," in Proceedings of the 22nd ACM Int. Conf. on Multimedia, Nov. 3-7, 2014, Orlando, FL, USA, Eds. ACM, 2014. pp. 675-678.
42. [42] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory, "Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
43. [43] S. Borovkova and I. Tsiamas, "An ensemble of LSTM neural networks for high‐frequency stock market classification, "Journal of Forecasting, vol. 38, no. 6, pp. 600-619, 2019.
44. [44] Z. Jin, Y. Yang, and Y. Liu, "Stock closing price prediction based on sentiment analysis and LSTM," Neural Computing and Applications, vol. 32, no. 13, pp. 9713-9729, 2020.
45. [45] A. Amidi and S. Amidi, "Recurrent Neural Networks cheatsheet," Available: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks [Accessed: March 9, 2023].
46. [46] K. Cho, V. Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation," ArXiv.org, 2014.
47. [47] M. A. Kızrak and B. Bolat, "Uçak Motoru Sağlığı için Uzun-Kısa Süreli Bellek Yöntemi ile Öngörücü Bakım," Bilişim Teknolojileri Dergisi, pp. 103-109, 2019.
48. [48] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling," ArXiv.org, 2014.
49. [49] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative Adversarial Networks," ArXiv.org, 2014.
50. [50] L. Lan, L. You, Z. Zhang, Z. Fan, W. Zhao, N. Zeng, Y. Chen, and X. Zhou, "Generative Adversarial Networks and Its Applications in Biomedical Informatics," Frontiers in Public Health, vol. 8, p. 164, 2020.
51. [51] A. You, J. K. Kim, I. H. Ryu, and T. K. Yoo, "Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey," Eye and Vision, vol. 9, no. 1, 2022.
52. [52] K. Wang, C. Gou, Y. Duan, Y. Lin, X. Zheng, and F. Y. Wang, "Generative adversarial networks: introduction and outlook," IEEE/CAA Journal of Automatica Sinica, vol. 4, no. 4, pp. 588-598, 2017.
53. [53] T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, "Improved Techniques for Training GANs," ArXiv.org, 2016.
54. [54] M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein GAN," ArXiv.org, 2017.
55. [55] Alphabet Inc. "Alphabet Inc. (GOOG) Stock Price, News, Quote and History - Yahoo Finance," Available: https://finance.yahoo.com/quote/GOOG/ [Accessed: March 9, 2023].
56. [56] B. Banushev, "Using the latest advancements in AI to predict stock market movements," Available: https://github.com/borisbanushev/stockpredictionai [Accessed: March 9, 2023].
57. [57] R. Dash, P. K. Dash, and R. Bisoi, "A self-adaptive differential harmony search based optimized extreme learning machine for financial time series prediction," Swarm and Evolutionary Computation, vol. 19, pp. 25-42, 2014.
58. [58] T. Fischer and C. Krauss, "Deep learning with long short-term memory networks for financial market predictions," European Journal of Operational Research, vol. 270, no. 2, pp. 654-669, 2018.
59. [59] I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to sequence learning with neural networks," in Advances in Neural Information Processing Systems, pp. 3104-3112, 2014.
60. [60] J. Sirignano and R. Cont, "Universal features of price formation in financial markets: perspectives from Deep Learning," Quantitative Finance, vol. 19, no. 8, pp. 1449-1459, 2018.
61. [61] F. A. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget: Continual prediction with LSTM," Neural Computation, vol. 12, no. 10, pp. 2451-2471, 2002.
62. [62] J. Lv, C. Wang, W. Gao, and Q. Zhao, "An Economic Forecasting Method Based on the LightGBM-Optimized LSTM and Time-Series Model," Computational Intelligence and Neuroscience, vol. 2021, pp. 1-10, 2021.
63. [63] F. J. Huang, W. Zhang, and T. Yoshida, "A hybrid model for stock price prediction," Quantitative Finance, vol. 18, no. 12, pp. 2001-2016, 2018.
64. [64] W. Zhang and T. Yoshida, "Stock price prediction based on generative adversarial network," Procedia Computer Science, vol. 169, pp. 101-108, 2020.
65. [65] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, "Improved Training of Wasserstein GANs," in Advances in Neural Information Processing Systems, vol. 30, pp. 5767-5777, 2017.
66. [66] J. Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in Proceedings of the IEEE Int. Conf. on Computer Vision, Oct. 22-29, 2017, Venice, Italy [Online]. Available: IEEE Xplore. [Accessed: Mar. 9, 2023].
67. [67] J. Xu, J. He, J. Gu, H. Wu, L. Wang, Y. Zhu, T. Wang, X. He, and Z. Zhou, "Financial Time Series Prediction Based on XGBoost and Generative Adversarial Networks," International Journal of Circuits, Systems and Signal Processing, vol. 16, pp. 637-645, 2022.