Gözde ŞİŞMANOĞLU, Furkan KOÇER, Mehmet Ali ÖNDE, Özgür Koray ŞAHİNGÖZ

Derin Öğrenme Yöntemleri ile Borsada Fiyat Tahmini

Son yıllarda, bilgisayarların donanımındaki teknolojik gelişmeler ve makine öğrenme tekniklerindeki gelişmelernedeniyle, "Büyük Veri" ve "Paralel İşleme" kullanımı olmak üzere problem çözmek için iki artan yaklaşım vardır.Özellikle GPU'lar gibi çok çekirdekli bilgi işlem aygıtlarında paralel olarak gerçekleştirilebilen Derin Öğrenmealgoritmalarının ortaya çıkmasıyla, bu yaklaşımlarla birçok gerçek dünya problemleri çözülebilmektedir. Derinöğrenme modelleri eğitildikleri veri ile sınıflandırma, regresyon analizi ve zaman serilerinde tahmin gibiuygulamalarda büyük başarılar göstermektedir. Bu modellerin finansal piyasadaki en aktif uygulama alanlarındanbiri özellikle borsada işlem gören hisse senetlerinin tahmini işlemleridir. Bu alanda amaç, pazardaki değişim sürecihakkındaki hisse senedinin önceki günlük verilerine bakarak kısa veya uzun vadeli gelecekteki değerini tahminetmeye çalışmaktır. Bu çalışmada, LSTM, GRU ve BLSTM isimli 3 farklı derin öğrenme modeli kullanılarak birhisse senedi tahmin sistemi geliştirilip, kullanılan modeller arasında karşılaştırmalı bir analiz yapıldı. Spekülatifhareketlerden uzak olması için veri seti olarak 1968'den 2018'e kadar olan New York Borsası'ndan hisse senedininzaman serisi değerleri kullanıldı. Spesifik olarakta IBM hisse senedi ile test çalışmaları yapıldı. Deneysel sonuçlar,hisse senedine ait son 5 günlük işlem verilerinin girdi olarak kullanıldığı BLSTM modeliyle yapılan eğitimin%63,54 lük bir yönsel doğruluk değerine ulaşıldığını göstermektedir.

Price Forecasting in Stock Exchange with Deep Learning Methods

In recent years, due to the technological advances in computer hardware and enhancements in machine learning techniques, there are two hot research areas in problem solving, the use of "Big Data" and "Parallel Processing". Many real-world problems can be solved with the use of different Deep Learning algorithms, which can be realized in parallel with multicore computing devices such as GPUs. Deep learning models show great success in applications such as classification of raw data, regression analysis and estimation in time series. One of the most active application areas of these models is “the financial market” which aims a good estimation of stock prices in the exchange market. In this paper, it is aimed to forecast the short or long term future value by looking at the previous log data of the stock on the process of change in the market. In this study, a price forecasting system was developed by using 3 different deep learning models named LSTM, GRU and BLSTM with a comparative analysis between them. The time series values of the stock were used from the New York Stock Exchange from 1968 to 2018 as a set of data to be free of speculative movements. Specifically, tests were conducted on IBM stock. Experimental results show that the directional accuracy of 63.54% was achieved with the BLSTM model where the last 5-day transaction data of the stock were used as input.

PDF

___

[1] Cavalcante R.C., Brasileiro R.C., Souza V.L., Nobrega J.P., Oliveira A.L. 2016. Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, 55: 194-211.
[2] Namdari A., Li Z.S. 2018. Integrating Fundamental and Technical Analysis of Stock Market through Multi-layer Perceptron. 2018 IEEE Technology and Engineering Management Conference (TEMSCON), Evanston, IL, 1-6. doi: 10.1109/TEMSCON.2018.8488440.
[3] Beyaz E., Tekiner F., Zeng X., Keane J. 2018. Comparing Technical and Fundamental Indicators in Stock Price Forecasting. 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), Exeter, United Kingdom, 1607-1613.
[4] Chou J., Nguyen T. 2018. Forward Forecast of Stock Price Using Sliding-Window MetaheuristicOptimized Machine-Learning Regression. in: IEEE Transactions on Industrial Informatics, 14 (7): 3132-3142.
[5] Lien Minh D., Sadeghi-Niaraki A., Huy H.D., Min K., Moon H. 2018. Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network. in: IEEE Access, 6: 55392-55404.
[6] Trelewicz J.Q. 2017. Big Data and Big Money: The Role of Data in the Financial Sector. in: IT Professional, 19 (3): 8-10.
[7] Mohammadi M., Al-Fuqaha A., Sorour S., Guizani M. 2018. Deep Learning for IoT Big Data and Streaming Analytics: A Survey. in: IEEE Communications Surveys & Tutorials, 20 (4): 2923- 2960.
[8] Korczak J., Hernes M. 2017. Deep Learning for Financial Time Series Forecasting in A-Trader System. Proceedings of the 2017 Federated Conference on Computer Science and Information Systems.
[9] Arévalo A., Niño J., Hernández G., Sandoval J. 2016. High-Frequency Trading Strategy Based on Deep Neural Networks. Intelligent Computing Methodologies Lecture Notes in Computer Science, 424-436.
[10] Zhou X., Pan Z., Hu G., Tang S., Zhao C. 2018. Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets. Mathematical Problems in Engineering, 2018: 1-11.
[11] Ganesh P., Rakheja P. 2018. Deep Neural Networks in High Frequency Trading, https://arxiv.org/pdf/1809.01506.pdf. (Erişim Tarihi: 01/12/2019).
[12] Gudelek M.U., Boluk S.A., Ozbayoglu 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, 1-8. doi: 10.1109/SSCI.2017.8285188.
[13] Karatas G., Demir O., Sahingoz O.K. 2018. Deep Learning in Intrusion Detection Systems. 2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT), Ankara, Turkey, 113-116.
[14] Sahingoz O.K., Baykal S.I., Bulut D. 2018. Phishing Detection From URLs By Using Neural Networks. Computer Science & Information Technology (CS & IT), SPPR, SCAI, CSIA, WiMoA, ICCSEA, InWeS, NECO, GridCom – 2018, Sydney, Australia, 41-54.
[15] Kumar S., Ningombam D. 2018. Short-Term Forecasting of Stock Prices Using Long Short Term Memory. 2018 International Conference on Information Technology (ICIT), Bhubaneswar, India, 182-186. doi: 10.1109/ICIT.2018.00046.
[16] Shao X., Ma D., Liu Y., Yin Q. 2017. Short-term forecast of stock price of multi-branch LSTM based on K-means. 2017 4th International Conference on Systems and Informatics (ICSAI), Hangzhou, 1546-1551. doi: 10.1109/ICSAI.2017.8248530.
[17] Sismanoglu G., Onde M.A., Kocer F., Sahingoz O.K. 2019. Deep Learning Based Forecasting in Stock Market with Big Data Analytics. 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), Istanbul, Turkey, 1-4.
[18] Zhong G., Zhang K., Wei H., Zheng Y., Dong J. 2019. Marginal Deep Architecture: Stacking Feature Learning Modules to Build Deep Learning Models. in: IEEE Access, 7: 30220-30233.