Predicting Market Direction With Deep Learning: An Application on E-7 Country Stock Markets

Yıl 2025, Sayı: 123, 92 - 111, 01.04.2025

Nazif Ayyıldız

Öz

This study aims to examine the prediction performance of the deep learning method on the stock indices of E-7 countries, known as emerging market economies. In this context, the daily movement directions of the stock indices of IPC (Mexico), SSE (China), BIST 100 (Turkey), RTS (Russia), BOVESPA (Brazil), IDX (Indonesia), and NIFTY 50 (India) were predicted using the H2O deep learning model. Technical indicators calculated based on the daily closing prices between 01.01.2015 and 31.12.2024 were used as inputs for the model. The data was split into 80% training and 20% test sets during the prediction process. The calculated accuracy rates were 88.47% for the IPC index, 78.13% for SSE, 77.29% for BIST 100, 76.05% for RTS, 75.81% for BOVESPA, 75.05% for IDX, and 74.34% for NIFTY 50. The findings demonstrate that deep learning methods can predict stock index movements with a certain level of accuracy.

Anahtar Kelimeler

Deep Learning, H2O Deep Learning Model, Classification, Developing Countries

Piyasa Yönünün Derin Öğrenme ile Tahmini: E-7 Ülke Borsaları Üzerine Bir Uygulama

Öz

Bu çalışmada, derin öğrenme yönteminin yükselen piyasa ekonomileri olarak bilinen E-7 ülkelerinin borsa endeksleri üzerindeki tahmin performansının incelenmesi amaçlanmıştır. Bu bağlamda, IPC (Meksika), SSE (Çin), BIST 100 (Türkiye), RTS (Rusya), BOVESPA (Brezilya), IDX (Endonezya) ve NIFTY 50 (Hindistan) borsa endekslerinin günlük hareket yönleri H2O derin öğrenme modeli kullanılarak tahmin edilmiştir. Modelin girdileri olarak, 01.01.2015 ve 31.12.2024 tarihleri arasında günlük kapanış fiyatlarına dayalı olarak hesaplanan teknik göstergeler kullanılmıştır. Tahmin sürecinde veriler %80 eğitim ve %20 test seti olarak bölünmüştür. Hesaplanan doğruluk oranları IPC endeksi için %88,47, SSE için %78,13, BIST 100 için %77,29, RTS için %76,05, BOVESPA için %75,81, IDX için %75,05 ve NIFTY 50 için %74,34 olarak bulunmuştur. Elde edilen bulgular, derin öğrenme yöntemlerinin borsa endeksi hareketlerini belirli bir doğruluk düzeyiyle tahmin edebildiğini göstermektedir.

Anahtar Kelimeler

Derin Öğrenme, H20 Derin Öğrenme Modeli, Sınıflandırma, Gelişmekte Olan Ülkeler.

Kaynakça

• Albayrak, E., & Saran, N. (2023). İstatistiksel ve Derin Öğrenme Modellerini Kullanarak Hisse Senedi Fiyat Tahmini. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 16(2), 161-169. https://doi.org/10.54525/tbbmd.1031017
• Alhazbi, S., Said AB & Al-Maadid, (2020) Using Deep Learning to Predict Stock Movements Direction in Emerging Markets: The Case of Qatar Stock Exchange, 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), Doha, Qatar, 440-444. https://doi.org/10.1109/ICIoT48696.2020.9089616
• Aliyev, F., Eylasov N. & Gasim, N. (2022) Applying Deep Learning in Forecasting Stock Index: Evidence from RTS Index, 2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT), Washington DC, DC, USA, 2022, 1-4. https://doi.org/10.1109/AICT55583.2022.10013496
• Altunbaş, C. (2021) Derin Öğrenme ile Hisse Senedi Piyasası Tahmini [Yüksek Lisans Tezi]. Adnan Menderes Üniversitesi, Sosyal Bilimler Enstitüsü.
• Arora, A., Candel, A., Lanford, J., Ledel, E., & Parmar, V. (2015). Deep Learning with H2O. H2O.ai, Erişim Tarihi:22.02.2024, DeepLearning_Vignette.pdf (h2o-release.s3.amazonaws.com)
• Ayyıldız. N. (2023) Prediction of Stock Market Movements with Machine Learning Index, Özgür Puplications. https://doi.org/10.58830/ozgur.pub354
• Ayyıldız ve İskenderoğlu (2024) How effective is machine learning in stock market predictions? Heliyon, 10(2). https://doi.org/10.1016/j.heliyon.2024.e24123
• Ayyıldız, N. (2024). Bankacılık Sektörüne Derin Öğrenme Yöntemiyle Bakış: BİST Banka Endeksi Hareket Yönlerinin Tahmini. İnsan ev Toplum Bilimleri Araştırmaları Dergisi, 13(3), 1277-1291. https://doi.org/10.15869/itobiad.1451709
• Beniwal, M., Singh, A. & Kumar, N. (2024). Forecasting multistep daily stock prices for long-term investment decisions: A study of deep learning models on global indices, Engineering Applications of Artificial Intelligence, 129. https://doi.org/10.1016/j.engappai.2023.107617
• Cui, C., Wang, P., Li, Y. & Zhang, Y. (2023), McVCsB: A new hybrid deep learning network for stock index prediction, Expert Systems with Applications, 232. https://doi.org/10.1016/j.eswa.2023.120902
• Çetin D. Ve Metlek S (2021). Türkiye’deki İslami Hisse Senedi Endeksinin, Endeks Tabanlı Öznitelikler Kullanılarak Derin Öğrenme Yöntemi ile Tahmini. Acta Infologica, 5(2), 287 - 298. http://dx.doi.org/10.26650/acin.975633
• Gudelek, M. U. Bölük S. A. & Özbayoğlu, A. M. (2017). A deep learning based stock trading model with 2-D CNN trend detection, 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA, pp. 1-8, http://dx.doi.org/10.1109/SSCI.2017.8285188
• Gündüz, H., Çataltepe, Z., & Yaslan, Y. (2017). Derin Sinir Ağları ile Borsa Yönü Tahmini, Stock Market Direction Prediction Using Deep Neural Networks, Signal Processing and Communications Applications Conference (SIU), İzmir.
• Han, J., Kamber, M. & Pei, J. (2012). Data Mining: Concepts and Techniques. Third Edition, Elsevier Science & Technology. USA.
• H20 (2024), H20 Deep Learning (Neural Networks), Erişim Tarihi:22.02.2024, https://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/deep-learning.html
• Kanwal, A., Lau,M.F., P.H. Ng,S., Sım,K.Y. & Chandrasekaran,S. (2022). BiCuDNNLSTM-1dCNN-A hybrid deep learning-based predictive model for stock price prediction, Expert Systems with Applications, 202. https://doi.org/10.1016/j.eswa.2022.117123.
• Kumbure, M.M., Lohrmann C., Luukka, P.& Porras, J.(2022). Machine learning techniques and data for stock market forecasting: A literature review, Expert Systems with Applications,197. https://doi.org/10.1016/j.eswa.2022.116659.
• Liu, Y, Zhou, Y. Wen, S. & Tang, C. (2014), A Strategy on Selecting Performance Metrics for Classifier Evaluation, International Journal of Mobile Computing and Multimedia Communication, 6, 20-35. http://dx.doi.org/10.4018/IJMCMC.2014100102
• Mallıkarjuna, M.& Rao, R.P. (2019), Evaluation of forecasting methods from selected stock market returns. Financ Innov 5(40). https://doi.org/10.1186/s40854-019-0157-x
• Najafabadi, M. M., Villanustre, F., Khoshgoftaar, T. M., Selıya, N., Wald, R., & Muharemagıc, E. (2015). Deep learning applications and challenges in big data analytics. Journal of big data, 2(1), 1-21. https://doi.org/10.1186/s40537-014-0007-7
• Nelson, D. M. Q. Pereıra A. C. M. & De Olıveıra, R. A. (2017) Stock market's price movement prediction with LSTM neural networks, 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, pp. 1419-1426. https://doi.org/10.1109/IJCNN.2017.7966019
• Noh Y, Kim J-M, Hong S, Kim S. (2023), Deep Learning Model for Multivariate High-Frequency Time-Series Data: Financial Market Index Prediction. Mathematics.; 11(16):3603. https://doi.org/10.3390/math11163603
• Prachyachuwong K, & Vateekul P. (2021) Stock Trend Prediction Using Deep Learning Approach on Technical Indicator and Industrial Specific, Information. Information. 12(6):250. https://doi.org/10.3390/info12060250
• Racz, A., Bajusz, D. & Heberger, K. (2021). Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR, Multiclass Classification, Molecules, 26, 1111. https://doi.org/10.3390/molecules26041111.
• Raşo, H. (2019). Deep Learning Based Stock Market Prediction Using Technical Indicators [Yüksek Lisans Tezi]. en Bilimleri Enstitüsü, Gazi Üniversitesi, Ankara.
• Santur, Y. (2020). Deep Learning Based Regression Approach for Algorithmic Stock Trading: A Case Study of the BIST30. Gümüşhane Üniversitesi Fen Bilimleri Dergisi, 10(4), 1195-1211. https://doi.org/10.17714/gumusfenbil.707088
• Sokolova, M. & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management. 45. 427-437. https://doi.org/10.1016/j.ipm.2009.03.002
• Stetsenko, P. (2017), Machine Learning with Python and H2O, Fifth Edition, Erişim Tarihi:22.02.2024, DeepLearning_Vignette.pdf (h2o-release.s3.amazonaws.com)
• Yang, C. Zhai, J. & Tao, G. (2020). Deep Learning for Price Movement Prediction Using Convolutional Neural Network and Long Short-Term Memory, Mathematical Problems in Engineering. https://doi.org/10.1155/2020/2746845
• Yiling, D., Ning, S., Jıahao, X., Pengyan, L., Jiaxin W. & Sai, T. (2022). Research on Shanghai Stock Exchange 50 Index Forecast Based on Deep Learning. Mathematical Problems in Engineering. 1-9. http://dx.doi.org/10.1155/2022/1367920
• Zhong, X., & Enke, D. (2019). Predicting the daily return direction of the stock market using hybrid machine learning algorithms, Financial Innovation, 5. https://doi.org/10.1186/s40854-019-0138-0.