Bütünleşik Dalgacık Dönüşümü-Evrişimsel Sinir Ağları Tabanlı Derin Öğrenme Yaklaşımı ve Borsa Tahmini Üzerine Bir Uygulama

Yıl 2023, , 387 - 404, 28.12.2023

Hamit Erdal , Selçuk Korucuk

https://doi.org/10.38155/ksbd.1258709

Öz

Finansal tahminleme çalışmalarında üzerinde en fazla çalışılan konulardan biri borsa tahminidir. Risk yoğun bir yatırım aracı olan borsa için iyi bir tahmin aracının veya metodolojisinin geliştirilebilmesi yatırımcılar için paha biçilemez önemdedir. Bu çalışmada, Borsa İstanbul Sınai endeksi günlük verisi ile bir borsa tahmini çalışması gerçekleştirilmiş ve borsanın açık olduğu 5.000 günlük (31.12.2001-31.12.2021) endeks açılış fiyatları kullanılarak tahmin için 3 model kurulmuştur. Model 1.’de 1 gün geriden gelen değerlerle, Model 2.’de 3 gün geriden gelen değerlerle ve Model 3.’de ise 7 gün geriden gelen değerlerle tahmin yapmıştır. Tahmin yöntemi olarak etkinliği pek çok çalışmada ortaya konulmuş bir derin öğrenme yöntemi olan Evrişimsel Sinir Ağları (ESA) ve Dalgacık Dönüşümü (DD) ile önişleme tabi tutulmuş ESA (DDESA) yöntemleri kullanılmıştır. Böylece durağan bir durum için veri kümesini alt kümelere ayrıştıran dalgacık dönüşümünün tahmin performansına etkisi araştırılmıştır. Çalışmanın sonucunda DDESA yaklaşımı ile tahmin başarısının artırılabildiği ve etkin bir tahminleme aracı olarak kullanılabileceği sonucuna ulaşılmıştır.

Anahtar Kelimeler

Borsa, Tahminleme, Derin Öğrenme, Dalgacık Dönüşümü, Evrişimsel Sinir Ağları

An Integrated Wavelet Transform-Convolutional Neural Network Based Deep Learning Approach and An Application On Stock Exchange Estimation

Öz

Stock market estimation is one of the most studied topics in financial estimation studies. Developing a better estimation tool or methodology for the stock market, which is a risk-intensive investment tool, is invaluable for investors. In this study, a stock market estimation study was carried out with the daily data of Borsa Istanbul (BIST) Industrial index (XUSIN). In this context, the opening prices of the 5,000-day index (31.12.2001-31.12.2021) were utilized and three models were developed for estimating. In Model 1, estimations were conducted with values that 1 day behind; in Model 2, with values that 3 days behind and in Model 3, with values that 7 days behind, respectively. Convolutional Neural Network (CNN) and Wavelet Transform Convolutional Neural Network (WTCNN), which are deep learning methods whose effectiveness has been demonstrated in many studies, were utilized as estimation methods. Thus, the effect of wavelet transforms which decomposes dataset into subsets for a stationary situation for estimation performance was investigated. It was concluded that the estimation success could be increased with the DDESA approach and it could be used as an effective estimation tool.

Anahtar Kelimeler

Stock Exchange, Estimation, Deep Learning, Wavelet Transform, Convolutional Neural Network

Kaynakça

• Aktaş, A., Doğan B. ve Demir, Ö. (2020). Tactile paving surface detection with deep learning methods. Journal of the Faculty of Engineering and Architecture of Gazi University, 35(3), 1685-1700.
• Atsalakis, G.S. ve Valavanis, K.P. (2009). Surveying stock market forecasting techniques–part II: Soft computing methods. Expert Systems with Applications, 36(3), 5932-5941.
• Aydoğmuş, H.Y., Ekinci, A., Erdal, H.İ. ve Erdal, H. (2015). Optimizing the monthly crude oil price forecasting accuracy via bagging ensemble models. Journal of Economics and International Finance, 7(5), 127-136.
• Aydoğmuş, H.Y., Erdal, H.İ., Karakurt, O., Namlı, E., Türkan, Y.S. ve Erdal, H. (2015). A comparative assessment of bagging ensemble models for modeling concrete slump flow. Computers and Concrete, 16(5), 741-757.
• Basak, S., Kar, S., Saha, S., Khaidem, L., ve Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552-567.
• Chen, H., Xiao, K., Sun, J. ve Wu, S. (2017). A double-layer neural network framework for high-frequency forecasting. ACM Transactions on Management Information Systems (TMIS), 7(4), 1-17.
• Cires, D.C., Meier, U., Masci, J., Gambardella, L.M. e Schmidhuber, J. (2012). High performance convolutional neural networks for image classification. Proceedings of 22nd International Joint Conference on Artificial Intelligence, 1237-1242.
• Chalus, P., Walter, S. ve Ulmschneider, M. (2007). Combined wavelet transform-artificial neural network use in tablet active content determination by near-infrared spectroscopy. Analytica Chimica Acta, 591(2), 219-224.
• Demirdöğen, O., Erdal, H. ve Akbaba, A.İ. (2017). Comparing various machine learning methods for prediction of patient revisit intention: A case study. Selçuk Üniversitesi Mühendislik Bilim ve Teknoloji Dergisi, 5(4), 386-401.
• Ding, G. ve Qin, L. (2019). Study on the prediction of stock price based on the associated network model of lSTM. International Journal of Machine Learning and Cybernetics, 1–11.
• Dingli, A. ve Fournier, K.S. (2017). Financial time series forecasting–a deep learning approach. International Journal of Machine Learning and Computing, 7, 118–122.
• Dong, Y., Li, S. ve Gong, X. (2017, April). Time series analysis: an application of ARIMA model in stock price forecasting. In 2017 International Conference on Innovations in Economic Management and Social Science (IEMSS 2017), Atlantis Press, 703-710.
• Effendi, K.A. (2015). Determining the best ARCH/GARCH model and comparing JKSE with stock index in developed countries. The Winners, 16(2), 71-84.
• Elmas, B. (2021). Türkiye’deki kelebek türlerinin basamaklı evrişimli sinir ağları ile sınıflandırılması. Konya Mühendislik Bilimleri Dergisi, 9(3), 568-587.
• Elmas, B. (2022). Evrişimli sinir ağları ile mermer & granit çeşitlerinin transfer öğrenme yöntemiyle sınıflandırılması. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 37(2), 985-1002.
• Erdal, H. (2021). Prediction of pipeline projects construction costs utilizing machine learning techniques. International Marmara Science and Social Sciences Congress-IMASCON 2021 SPRING, 21-22 Mayıs 2021, Derince, Kocaeli.
• Erdal, H., Erdal, M., Şimşek, O. ve Erdal, H.İ. (2018). Prediction of concrete compressive strength using non-destructive test results. Computers and Concrete, 21(4), 407-417.
• Erdal, H. ve Karahanoğlu, İ. (2016). Bagging ensemble models for bank profitability: An emprical research on Turkish development and investment banks. Applied Soft Computing, 49, 861-867.
• Erdal, H.I., Karakurt, O. ve Namlı, E. (2013). High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform. Engineering Applications of Artificial Intelligence, 26(4), 1246-1254.
• Fayeem, A., Kumar, A., Sagar, R., Aggarwal, A. ve Jain, D. (2022). Stock price prediction: Recurrent neural network in financial market. International Journal for Modern Trends in Science and Technology, 8(01), 259-264.
• Goodfellow, I., Bengio, Y. ve Courville, A. (2015). Deep learning. The MIT Press, Cambridge, Massachusetts, United States.
• Huang, J. Y. ve Liu, J. H. (2020). Using social media mining technology to improve stock price forecast accuracy. Journal of Forecasting, 39(1), 104-116.
• Jain, S., Gupta, R. ve Moghe, A. A. (2018, December). Stock price prediction on daily stock data using deep neural networks. In 2018 International conference on advanced computation and telecommunication (ICACAT), IEEE, 1-13.
• Jiang, W. (2021). Applications of deep learning in stock market prediction: recent progress. Expert Systems with Applications, 184, 115537.
• Kirişçi, M. ve Yolcu, O. (2022). A new CNN-based model for financial time series: TAIEX and FTSE stocks forecasting. Neural Processing Letters, 1-18.
• Kumar, I., Dogra, K., Utreja, C. ve Yadav, P. (2018, April). A comparative study of supervised machine learning algorithms for stock market trend prediction. In 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), IEEE, 1003-1007.
• Manojlović, T., ve Štajduhar, I. (2015, May). Predicting stock market trends using random forests: A sample of the Zagreb stock exchange. In 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (pp. 1189-1193). IEEE.
• Matiz, S. ve Barner, K. E. (2019). Inductive conformal predictor for convolutional neural networks: Applications to active learning for image classification. Pattern Recognition, 90, 172-182.
• Mehta, P., Pandya, S. ve Kotecha, K. (2021). Harvesting social media sentiment analysis to enhance stock market prediction using deep learning. PeerJ Computer Science, 7, e476.
• Misra, M., Yadav, A. P. ve Kaur, H. (2018, July). Stock market prediction using machine learning algorithms: A classification study. In 2018 International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering (ICRIEECE), IEEE, 2475-2478.
• Muruganandham, R., Karthikeyan, M. S., Jagajeevan, R. ve Chitra, R. (2021). Deep learning-based forecast using RNN for stock price prediction. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(14), 4939-4954.
• Namlı, E., Erdal, H.İ. ve Erdal, H. (2016). Dalgacık dönüşümü ile beton basınç dayanım tahmininin iyileştirilmesi. Politeknik Dergisi, 19(4), 471-480.
• Nayak, A., Pai, M. M., ve Pai, R. M. (2016). Prediction models for Indian stock market. Procedia Computer Science, 89, 441-449.
• Nti, I.K., Adekoya, A.F. ve Weyori, B.A. (2020). A systematic review of fundamental and technical analysis of stock market predictions. Artificial Intelligence Review, 53(4), 3007-3057.
• Ökten, İ. e Yüzgeç, U. (2022). Evrişimli sinir ağı ile çeltik bitkisi hastalığının tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 11(1), 203-217.
• Pabuçcu, H. (2019). Borsa endeksi hareketlerinin makine öğrenme algoritmaları ile tahmini. Uluslararası İktisadi & İdari İncelemeler Dergisi, 23, 179-190.
• Pahwa, K. ve Agarwal, N. (2019, February). Stock market analysis using supervised machine learning. In 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), IEEE, 197-200.
• Pasupulety, U., Anees, A. A., Anmol, S. ve Mohan, B. R. (2019, June). Predicting stock prices using ensemble learning and sentiment analysis. In 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), IEEE, 215-222.
• Patil, P., Wu, C.S.M., Potika, K. ve Orang, M. (2020, January). Stock market prediction using an ensemble of graph theory, machine learning and deep learning models. Proceedings of the 3rd International Conference on Software Engineering and Information Management, IEEE, 85-92.
• Sable, S., Porwal, A., ve Singh, U. (2017, April). Stock price prediction using genetic algorithms and evolution strategies. In 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA) (Vol. 2, pp. 549-553). IEEE.
• Saravanan, N. ve Ramachandran, K. I. (2010). Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert Systems with Applications, 37(6), 4168-4181.
• Shah, A., ve Bhavsar, C. (2015). Predicting Stock Market using Regression Technique. Research Journal of Finance and Accounting, 6(8), 27-34.
• Shen, S., Jiang, H., ve Zhang, T. (2012). Stock market forecasting using machine learning algorithms. Department of Electrical Engineering, Stanford University, Stanford, CA, 1-5.
• Shi, Z., Hu, Y., Mo, G. ve Wu, J. (2022). Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction. Journal of Latex Class Files, 14(8), 1-7, arXiv preprint arXiv:2204.02623.
• Singh, S., Madan, T. K., Kumar, J. ve Singh, A. K. (2019, July). Stock market forecasting using machine learning: Today and tomorrow. In 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), IEEE, 1, 738-745.
• Song, Y. ve Lee, J. (2019, December). Design of stock price prediction model with various configuration of input features. Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud Computing, IEEE, 1-5.
• Soni, P., Tewari, Y. ve Krishnan, D. (2022). Machine learning approaches in stock price prediction: A systematic review. In Journal of Physics: Conference Series, IOP Publishing, 2161(1), 012065.
• Soni, S. (2011). Applications of ANNs in stock market prediction: a survey. International Journal of Computer Science & Engineering Technology, 2(3), 71-83.
• Taşçıkaraoğlu, A., Sanandaji, B. M., Poolla, K. & Varaiya, P. (2016). Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using wavelet transform. Applied Energy, 165, 735-747.
• Uğur, L.O., Kanıt, L., Erdal, H., Namlı, E., Erdal, H.İ., Baykan, U.N. ve Erdal, M. (2019). Enhanced predictive models for construction costs: A case study of Turkish mass housing sector. Computational Economics, 53 (4), 1403-1419.
• Valle-Cruz, D., Fernandez-Cortez, V., López-Chau, A. ve Sandoval-Almazán, R. (2022). Does twitter affect stock market decisions? financial sentiment analysis during pandemics: A comparative study of the h1n1 and the covid-19 periods. Cognitive Computation, 14 (1), 372-387.
• Wang, H., Wang, J., Cao, L., Li, Y., Sun, Q. ve Wang, J. (2021). A stock closing price prediction model based on CNN-BiSLSTM. Complexity, 2021 (1), 1-12.
• Wang, N. ve Adeli, H. (2015). Self-constructing wavelet neural network algorithm for nonlinear control of large structures. Engineering Applications of Artificial Intelligence, 41, 249-258.
• Werawithayaset, P. ve Tritilanunt, S. (2019, November). Stock closing price prediction using machine learning. In 2019 17th International Conference on ICT and Knowledge Engineering (ICT&KE), IEEE, 1-8.
• Xingzhou, L., Hong, R. ve Yujun, Z. (2019, July). Predictive modeling of stock indexes using machine learning and information theory. Proceedings of the 2019 10th International Conference on E-business, Management and Economics, IEEE, 175-179.
• Xu, Y. ve Keselj, V. (2019, December). Stock prediction using deep learning and sentiment analysis. In 2019 IEEE International Conference on Big Data (Big Data), IEEE, 5573-5580.
• Yapraklı, T.Ş. ve Erdal, H. (2015). Bankacılık sektöründe pazarlama karması elemanlarının önceliklerinin belirlenmesi: Erzurum ili örneği. The Journal of Academic Social Science Studies, 38, 481-500.