Derin Öğrenme Tabanlı Görüntü Sınıflandırma Yaklaşımı ile Borsa İstanbul 100 Endeks Yönünün Tahmini

Öz

Borsa endeksleri, genel ekonomik performansı yansıttıkları için yatırımcılar tarafından yatırım kararları alırken önemli bir referans olarak kullanılırlar. Ayrıca, portföy yönetim şirketlerinin endeksleri replike eden yatırım fonları, hisse senetleri gibi gerçek zamanlı olarak alınıp satılabilir. Bu nedenle, borsa endeksinin gelecekteki yönünü tahmin etmek, yatırımcılar için kritik bir öneme sahiptir. Bu çalışmada, Borsa İstanbul 100 (BIST100) endeksinin yön tahmininde derin öğrenme tabanlı bir görüntü sınıflandırma yaklaşımı önerilmiştir. İlk olarak, günlük BIST100 endeks değerleri bir sonraki günün endeks değeri ile karşılaştırılarak yukarı ve aşağı şeklinde etiketlendi. Etiketlenen veriler daha sonra teknik analiz göstergeleri kullanılarak grafik görüntülerine dönüştürüldü. Tahmin modeli için, ön-eğitimli evrişimsel sinir ağı (CNN) modelleri olan AlexNet, GoogLeNet ve ResNet-50, problemle uyumlu hale getirilmek üzere ince ayarlandı. Eğitim dışı bırakılan üç yıllık dönem boyunca ince-ayarlama yapılmış AlexNet, GoogLeNet ve ResNet-50 modelleri sırasıyla %54,22, %53,01 ve %54,62 doğruluk değerleri ile BIST100 endeks yönünü tahmin edebilmiştir. Ayrıca, modellerin performansını değerlendirmek için Naive karşılaştırma yöntemi kullanıldı. Deneysel sonuçlar, ince ayarlı her üç CNN modelinin Naive karşılaştırma yönteminden daha iyi sonuçlar elde ettiğini göstermektedir.

Anahtar Kelimeler

• BIST100
• Finansal zaman serisi analizi
• Derin öğrenme
• Evrişimsel sinir ağları
• Transfer öğrenme.

Prediction of Borsa Istanbul 100 Index Direction via Deep Learning Based Image Classification Approach

Öz

Stock market indices are used as a significant reference by investors when making investment decisions, as they reflect the overall economic performance. Additionally, portfolio management companies' investment funds that replicate indices can be bought and sold in real time, similar to stocks. Therefore, predicting the future direction of the stock market index is of critical importance for investors. In this study, a deep learning-based image classification approach is proposed for predicting the direction of the Borsa Istanbul 100 (BIST100) index. Initially, daily BIST100 index values were labeled as up or down by comparing them with the index value of the following day. The labeled data was then transformed into graphic images using technical analysis indicators. For the prediction model, pre-trained Convolutional Neural Network (CNN) models, namely AlexNet, GoogLeNet, and ResNet-50, were fine-tuned to adapt to the problem. Fine-tuned AlexNet, GoogLeNet, and ResNet-50 models achieved accuracy values of 54.22%, 53.01%, and 54.62%, respectively, in predicting the direction of the BIST100 index during the three-year out-of-sample period. Additionally, the Naive comparison method was used to evaluate the performance of the models. Experimental results indicate that all three fine-tuned CNN models outperformed the Naive comparison method.

Anahtar Kelimeler

• BIST100
• Financial time series analysis
• Deep learning
• Convolutional neural networks
• Transfer learning.

Kaynakça

1. Achelis, S. B. (2001). Technical Analysis from A to Z. McGraw Hill New York.
2. Albuquerque, P. H. M., Peng, Y., Silva, J. P. F. da. (2022). Making the whole greater than the sum of its parts: A literature review of ensemble methods for financial time series forecasting. Journal of Forecasting, 41(8), 1701–1724. https://doi.org/10.1002/FOR.2894
3. Altuntaş, Y., Okumuş, F., Kocamaz, A. F. (2022). Evrişimsel Sinir Ağları ve Transfer Öğrenme Yaklaşımı Kullanılarak Altın Fiyat Yönünün Tahmini. Journal of Computer Science, 7(2), 124–131. https://doi.org/10.53070/bbd.1205299
4. Bhandari, H. N., Rimal, B., Pokhrel, N. R., Rimal, R., Dahal, K. R., Khatri, R. K. C. (2022). Predicting stock market index using LSTM. Machine Learning with Applications, 9, 100320. https://doi.org/10.1016/J.MLWA.2022.100320 Borsa Istanbul. (2020). BIST Pay Endekslerinden İki Sıfır Atılıyor. https://www.borsaistanbul.com/tr/duyuru/2860/bist-pay-endekslerinden-iki-sifir-atiliyor. Erişim Tarihi: 15 Kasım 2023.
5. Bukhari, A. H., Raja, M. A. Z., Sulaiman, M., Islam, S., Shoaib, M., Kumam, P. (2020). Fractional neuro-sequential ARFIMA-LSTM for financial market forecasting. IEEE Access, 8, 71326–71338. https://doi.org/10.1109/ACCESS.2020.2985763
6. Cavalcante, R. C., Brasileiro, R. C., Souza, V. L. F., Nobrega, J. P., Oliveira, A. L. I. (2016). Computational Intelligence and Financial Markets: A Survey and Future Directions. Expert Systems with Applications, 55, 194–211. https://doi.org/10.1016/j.eswa.2016.02.006
7. Dixon, M. F., Halperin, I., Bilokon, P. (2020). Machine learning in finance: From theory to practice. Machine Learning in Finance: From Theory to Practice, 1–548. https://doi.org/10.1007/978-3-030-41068-1/COVER
8. Durairaj, D. M., Mohan, B. H. K. (2022). A convolutional neural network based approach to financial time series prediction. Neural Computing and Applications, 34(16), 13319–13337. https://doi.org/10.1007/S00521-022-07143-2/TABLES/16

9. Durairaj, M., Krishna Mohan, B. H. (2019). A review of two decades of deep learning hybrids for financial time series prediction. International Journal on Emerging Technologies, 10(3), 324–331.
10. Gong, Y., Ming-Tai Wu, J., Li, Z., Liu, S., Sun, L., Chen, C. M. (2022). A CNN-Based Method for AAPL Stock Price Trend Prediction Using Historical Data and Technical Indicators. Smart Innovation, Systems and Technologies, 268, 25–33. https://doi.org/10.1007/978-981-16-8048-9_3/COVER
11. Gündüz, H., Yaslan, Y., Çataltepe, Z. (2018). Finansal haberler kullanılarak derin öǧrenme ile borsa tahmini. 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, 1–4. https://doi.org/10.1109/SIU.2018.8404616
12. He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.
13. Fawaz, H.I., Forestier, G., Weber, J., Idoumghar, L., Muller, P. A. (2019). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery 2019 33:4, 33(4), 917–963. https://doi.org/10.1007/S10618-019-00619-1
14. Khodaee, P., Esfahanipour, A., Mehtari Taheri, H. (2022). Forecasting turning points in stock price by applying a novel hybrid CNN-LSTM-ResNet model fed by 2D segmented images. Engineering Applications of Artificial Intelligence, 116, 105464. https://doi.org/10.1016/J.ENGAPPAI.2022.105464
15. Kirisci, M., Cagcag Yolcu, O. (2022). A New CNN-Based Model for Financial Time Series: TAIEX and FTSE Stocks Forecasting. Neural Processing Letters, 54(4), 3357–3374. https://doi.org/10.1007/S11063-022-10767-Z/FIGURES/8
16. Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in neural information processing systems, 25.
17. Lecun, Y., Bengio, Y., Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
18. Li, A. W., Bastos, G. S. (2020). Stock market forecasting using deep learning and technical analysis: A systematic review. IEEE Access, 8, 185232–185242. https://doi.org/10.1109/ACCESS.2020.3030226
19. Mehtab, S., Sen, J. (2022). Analysis and Forecasting of Financial Time Series Using CNN and LSTM-Based Deep Learning Models. Lecture Notes in Networks and Systems, 302, 405–423. https://doi.org/10.1007/978-981-16-4807-6_39/COVER
20. Moghar, A., Hamiche, M. (2020). Stock Market Prediction Using LSTM Recurrent Neural Network. Procedia Computer Science, 170, 1168–1173. https://doi.org/10.1016/J.PROCS.2020.03.049
21. Ozbayoglu, A. M., Gudelek, M. U., Sezer, O. B. (2020). Deep learning for financial applications : A survey. Applied Soft Computing, 93, 106384. https://doi.org/10.1016/J.ASOC.2020.106384
22. Sezer, Ö. B., Güdelek, M. U., Özbayoğlu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing Journal, 90, 106181. https://doi.org/10.1016/j.asoc.2020.106181
23. Sezer, Ö. B., Özbayoğlu, A. M. (2018). Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach. Applied Soft Computing Journal, 70, 525–538. https://doi.org/10.1016/j.asoc.2018.04.024
24. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9.
25. Yoo, S., Jeon, S., Jeong, S., Lee, H., Ryou, H., Park, T., Choi, Y., Oh, K. (2021). Prediction of the Change Points in Stock Markets Using DAE-LSTM. Sustainability 2021, Vol. 13, Page 11822, 13(21), 11822. https://doi.org/10.3390/SU132111822