Stock Price Forecasting with Deep Learning Techniques

Year 2023, Volume: 11 Issue: 2, 137 - 156, 31.12.2023

Özgür Saracık , Aynur İncekırık

https://doi.org/10.17093/alphanumeric.1357466

Abstract

In this study, LSTM (Long-Short Term Memory) and GRU (Gated Recurrent Unit) techniques of deep learning, which are among the latest advanced technologies, were applied in the Google Colab software program for stock price forecasting. The dataset used in the study was obtained from Yahoo Finance and covers the dates between 02/01/2013 and 30/12/2022. Forecast models were created by considering 5 companies belonging to the XELKT (Electricity Market in Borsa Istanbul) index, which is part of BIST (Borsa Istanbul). Subsequently, the success of these forecast models was tested with the calculated model performance criteria, aiming to determine whether the techniques used were successful in stock price forecasting. Additionally, based on the results of MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Error) among the calculated model performance criteria, the techniques used were compared with each other, aiming to determine which of these techniques provided forecasts with less error. Then, through the analysis conducted on four different days, an attempt was made to identify the day that yielded the most successful forecasts. As a final step, the goal was to find a model with the least error based on techniques, epoch number, and the number of days forecasted, considering both MSE and MAPE for stocks. Since the model performance criteria outputs obtained from these analyses are below 1 for MSE and below 5% for MAPE, it can be concluded that both techniques demonstrate successful stock price forecasting. Consequently, in the comparison between these two techniques, it is observed that the LSTM technique is slightly more successful than the GRU technique.

Keywords

Deep Learning, Stock Price Forecasting, LSTM, GRU, BIST, XELKT

Ethical Statement

Sayın Editör, Bu makale birinci sırada yer alan yazar Özgür SARACIK'ın 2023 yılı temmuz ayında yayınlanmış olan "DERİN ÖĞRENME TEKNİKLERİ KULLANILARAK HİSSE SENEDİ FİYATLARININ TAHMİN EDİLMESİ: BIST’TE BİR UYGULAMA" isimli Yüksek Lisans tezinden türetilmiştir. Bilgilerinize sunarız. Saygılarımızla

References

• Adaş, E. B., & Erbay, B. (2022). An Evaluation on the Sociology of AI. Gaziantep University Journal of Social Sciences, 326 - 337.
• Aktürk, C., & Talan, T. (2022). Bilgisayar Bilimlerinde Teorik ve Uygulamalı Araştırmalar. Efe Akademi.
• Amidi, A., & Amidi, S. (2018). VIP Cheatsheet: Recurrent Neural Networks. https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks (Accessed: 03/01/2023)
• Arslan, K. (2020). AI and Applications in Education. Western Anatolia Journal of Educational Sciences, 71 - 88.
• Asher, C. (2021). The Role of AI in Characterizing the DCM phenotype. Frontiers in Cardiovascular Medicine, 1-20.
• Aslan, B. (2020). Derin Öğrenme ile Borsa Verileri Üzerine Tahminleme Yapılması (Yüksek Lisans Tezi). İzmir: Ege Üniversitesi Fen Bilimlei Enstitüsü.
• Athaiya, A., Sharma, S., & Sharma, S. (2020). Activation Function in Neural Networks. International Journal of Engineering Applied Sciences and Technology, 310 - 316.
• Aytekin, G. K. (2018). Türkiye’ de Sermaye Piyasaları ve Borsaların Gelişim Süreci. International Journal of Humanities and Education, 150-176.
• Bakkal, M., Bakkal, S., & Öztürk, Ş. Ş. (2012). Sermaye Piyasalarında Hisse Senetleri ve Hisse Senetlerini Etkileyen Makroekonomik Faktörler. Hiperlink Yayınları.
• Borsa İstanbul. (2023). https://www.borsaistanbul.com/Dosyalar/25yil/index.html (Accessed: 20/03/2023)
• Brownlee, J. (2017). Long Short-Term Memory Networks With Python. Machine Learnig Mystery.
• Durmuş, B. (2023, Nisan). Adaboost - Bagging Sınıflandırıcısını İyileştirmeye Yönelik Hibrit Bir Örnekleme Alogritması: Sağlık Alanında Bir Uygulama (Doktora Tezi). Muğla: Muğla Sıtkı Koçman Üniversitesi Fen Bilimleri Enstitüsü.
• Erden, C. (2021). Python ile Veri Madenciliği. İstanbul: İnkilap Kıtabevi.
• Fama, E. F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 383-417.
• Gosh, T. K., & Prelas, M. A. (2009). Energy Resources and Systems Volume 1: Fundamentals and Non-Renewable Resources. Springer.
• Güney, E. N. (2022). Derin Öğrenmede İstatistiksel Yöntemlerle Hisse Senedi Fiyatı Öngörüsü (Yüksek Lisans Tezi). Süleyman Demirel Üniversitesi.
• Jiang, H., & Peng, Y. (2016). Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 373-379. Arxiv
• Kamuyu Aydınlatma Platformu. (2023). Endeksler. https://www.kap.org.tr/tr/Endeksler (Accessed: 22/03/2023)
• Karadağ, K. (2022). Hibrit Derin Öğrenme Modelleri ile Hisse Senedi Fiyat Tahmini (Yüksek Lisans Tezi). Edirne: Trakya Üniversitesi.
• Kayaalp, K., & Süzen, A. A. (2020). Derin Öğrenme ve Türkiye’deki Uygulamaları. İstanbul: İksad Publishing House.
• Krenker, A., Bester, J., & Kos, A. (2011). Introduction to the Artificial Neural Networks. Artificial Neural Networks - Methodological Advances and Biomedical Applications, 1 - 18. IntechOpen.
• Kuş, Z. (2019). Mikrokanonikal Optimizasyon Algoritması ile Konvolüsyonel Sinir Ağlarında Hiper Parametrelerin Optimize Edilmesi (Yüksek Lisans Tezi). İstanbul: Fatih Sultan Mehmet Vakıf Üniversitesi.
• Lo, A. W.-C., & MacKinlay, A. C. (1999). A Non-Random Walk Down Wall Street. New Jersey: Princeton University Press.
• Madan, P., & Madhavan, S. (2020). An introduction to deep learning. IBM: https://developer.ibm.com/articles/an-introduction-to-deep-learning/ (Accessed: 19/03/2023)
• Malkiel, B. G. (2003). The Effcient Market Hypothesis and Its Critics. Journal of Economic Perspectives, 59 - 82.
• Mason, J. E., Traore, I., & Woungang, I. (2016). Machine Learning Techniques for Gait Biometric Recognition Using the Ground Reaction Force. Springer.
• McCorduck, P. (2004). Machines who think: A personal inquiry into the history and prospects of AI. Massachusetts: A. K. Peters Publishing.
• McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 115 - 133.
• Mehtab, S., & Sen, J. (2020). Stock Price Prediction Using CNN and LSTM - Based Deep Learning Models . DASA, 1 - 7. Bahrain.
• Metin, İ. A., & Karasulu, B. (2019). İnsan Aktivitelerinin Sınıflandırılmasında Tekrarlayan Sinir Ağı Kullanan Derin Öğrenme Tabanlı Yaklaşım. Veri Bilimi Dergisi, 1 - 10.
• Moghar, A., & Hamche, M. (2020). Stock Market Prediction Using LSTM Recurrent Neural Network. IWSMAI 2020 (s. 1168 - 1173). Warsaw: Procedia.
• Montasham, J. (2015). Renewable Energies. International Conference on Technologies and Materials for Renewable Energy, Environment and Sustainability (s. 1289 - 1297). ScienceDirect.
• Newell, A., Simon, H., & Shaw, J. C. (1959). Report on a General Problem Solving Program. Pittsburgh: Carnegie Institute of Technology
• Ozan, M. (2021). Derin Öğrenme Teknikleri Kullanılarak Borsadaki Hisse Değerlerinin Tahmin Edilmesi (Yüsek Lisans Tezi). Kayseri: Erciyes Üniversitesi Fen Bilimleri Enstitüsü.
• Özçalık, M., & Özçalık, S. G. (2020). Turizm Endeksinde Döviz Kuru Etkisi: BİST' te Bir Uygulama. Ekonomi, Politika & Finans Araştırmaları Dergisi, 374 - 388
• Öztürk, K., & Şahin, M. E. (2018). Yapay Sinir Ağları ve Yapay Zeka' ya Genel Bir Bakış. Takvim-i Vekayi, 25-36.
• Persio, L. D., & Honchar, O. (2017). Analysis of Recurrent Neural Networks for Short-Term Energy Load Forecasting. Computational Methods in Sciences and Engineering, 1 - 4.
• Raschka, S., & Mirjalili, V. (2017). Python Machine Learning. Birmingham: Packt Publishing.
• Saracık, Ö. (2023). Derin Öğrenme Teknikleri Kullanılarak Hisse Senedi Fiyatlarının Tahmin Edilmesi: BİST’te Bir Uygulama (Yüksek Lisans Tezi). Manisa: Manisa Celal Bayar Üniversitesi Sosyal Bilimler Enstitüsü.
• Schultz, D. P., & Schultz, S. E. (2011). A History of Modern Psychology (10th Edition). Belmont: Wadsworth Cengage Learning.
• Seyyarer, E., Ayata, F., Uçkan, T., & Karcı, A. (2020). Derin Öğrenmede Kullanilan Optimizasyon Algoritmalarinin Uygulanmasi ve Kıyaslanması. Anatolian Journal of Computer Sciences, 90-98.
• Shannon, C. (1949). Programming a Computer for Playing Chess. National IRE Convention, (s. 1 -18). New York.
• Song, H., & Choi, H. (2023). Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models. Applied Sciences, 1 - 26
• Şişmanoğlu, G., Koçer, F., Önde, M. A., & Şahingöz, Ö. K. (2020). Derin Öğrenme Yöntemleri ile Borsada Fiyat Tahmini. BEÜ Fen Bilimleri Dergisi, 434 - 445
• T.C. Enerji ve Tabii Kaynaklar Bakanlığı. (2023). https://enerji.gov.tr/bilgi-merkezi-enerji (Accessed: 03/02/2023)
• T.C. Resmi Gazete. (2014). Borsa İstanbul A.Ş. Borsacılık Faaliyetlerine İlişkin Esaslar Yönetmeliği.
• Turing, A. M. (1950). Computing machinery and intelligence. Mind a Quarterly Review of Psychology and Philosophy. 433 - 460
• Türk Ulusal Bilim e-Altyapısı (2023). https://docs.truba.gov.tr/education/keras/build/train.html (Accessed: 16/06/2023)
• Vasilev, I., Slater, D., Spacagna, G., Roelants, P., & Zocca, V. (2019). Python Deep Learning. Birmingham: Packt Publishing.
• Weizenbaum, J. (1966). ELIZA—a computer program for the study of natural language communication between man and machine. Commun. ACM, 36 - 45.
• Yılmaz, A., & Kaya, U. (2019). Derin Öğrenme. İstanbul: İnkilap Kitabevi.
• Yussif, A.-R. B. (2020). Yapay Sinir Ağları İle Borsa Endeksi Tahmini: Gana Borsası Üzerine Bir Uygulama (Yüksek Lisans Tezi). Konya: Selçuk Üniversitesi Sosyal Bilimler Enstitüsü.
• Zaheer, R., & Shaziya, H. (2019). A Study of the Optimization Algorithms in Deep Learning. International Conference on Inventive Systems and Control, 536 - 539. IEEE.