Research Article
BibTex RIS Cite

Derin Öğrenme Mimarisi Kullanarak BİST30 İndeksinin Tahmini

Year 2019, Volume: 4 Issue: 2, 106 - 121, 29.10.2019

Abstract

Derin
öğrenme yöntemleri, süreci hızlandırmak ve işlem adımlarındaki doğruluğu
sağlamak amacıyla, verilerdeki karmaşık kalıpları ve veriler arasındaki
etkileşimleri otomatik olarak algılayıp analiz edebilmektedir. Derin öğrenme
yöntemlerinin finans alanında uygulanması, bilgiye mümkün olduğunca hızlı ve
doğru bir şekilde ulaşma ihtiyacını karşılama noktasında faydalı olacaktır.
Ayrıca bu yöntemlerin kullanımı sayesinde, karmaşık ve etkileşimli büyük veri
kümelerini bünyesinde barındıran, menkul kıymetlerin tasarlanması ve
fiyatlandırılması, optimal portföyün oluşturulması ve finansal risk yönetiminin
gerçekleştirilmesi gibi finansal tahmin problemlerinin çözümü de
kolaylaşacaktır. Bu çalışma, derin öğrenme mimarisi yardımıyla BİST 30
Endeksinin günlük hareket tahminini elde etmeyi amaçlamaktadır.

References

  • Aslan, S., Badem, H., Özcan, T., Karaboğa, D., ve Baştürk, A. (2015). Çoklu Ekran Kartı ile Hızlandırılmış Ayrık Haar Dalgacık Dönüşümü Temelli Görüntü Şıkıştırma. Kahramanmaras Sutcu Imam University Journal of Engineering Sciences, 18(2), 12-16.
  • Buduma, N., ve Locascio, N. (2017). Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms. Boston: O'Reilly Media, Inc.
  • Canyılmaz, M., Türk, M., ve Güzel, E. (2016). Uzaktan Algılanan Düşük Frekanslı Sinyallerin Gürültülerinin Giderilmesinde Dalgacık Dönüşümü Ailelerinin Performanslarının İncelenmesi ve Karşılaştırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 73-77.
  • Chung, H., ve Shin, K.-s. (2018). Genetic algorithm-optimized long short-term memory network for stock market prediction. Sustainability, 10(10), 3765-3782. doi:10.3390/su10103765
  • Ciaburro, G., ve Venkateswaran, B. (2017). Neural Networks with R: Smart models using CNN, RNN, deep learning, and artificial intelligence principles. Birmingham: Packt Publishing Ltd.
  • Çalişan, M., ve Talu, M. F. (2017). Examination of the Effect of the Basic parameters of the Auto-encoder on Coding Performance. Paper presented at the 2017 International Artificial Intelligence and Data Processing Symposium (IDAP).
  • Derbeko, P., Dolev, S., ve Gudes, E. (2018). Privacy via Maintaining Small Similitude Data for Big Data Statistical Representation. Paper presented at the International Symposium on Cyber Security Cryptography and Machine Learning, Beer Sheva, Israel.
  • Erdogan, H., Hershey, J. R., Watanabe, S., ve Le Roux, J. (2017). Deep Recurrent Networks for Separation and Recognition of Single-Channel Speech in Nonstationary Background Audio. In New Era for Robust Speech Recognition (ss. 165-186): Springer.
  • Gurjar, M., Naik, P., Mujumdar, G., ve Vaidya, T. (2018). Stock Market Prediction Using ANN. International Research Journal of Engineering and Technology, 5(3), 2758-2761.
  • Heaton, J. (2015). Artificial Intelligence for Humans, Volume 3: Neural Networks and Deep Learning (Vol. 3). Chesterfield: Heaton Research, Inc.
  • Heaton, J. B., Polson, N. G., ve Witte, J. H. (2017). Deep Learning for Finance: Deep Portfolios. Applied Stochastic Models in Business Industry, 33(1), 3-12.
  • Hsieh, T.-J., Hsiao, H.-F., ve Yeh, W.-C. (2011). Forecasting Stock Markets Using Wavelet Transforms and Recurrent Neural Networks: An Integrated System Based on Artificial Bee Colony Algorithm. Applied soft computing, 11(2), 2510-2525.
  • Kannadasan, K., Edla, D. R., ve Kuppili, V. (2018). Type 2 Diabetes Data Classification Using Stacked Autoencoders in Deep Neural Networks. Clinical Epidemiology Global Health.
  • Kaynar, O., Aydın, Z., ve Görmez, Y. (2017). Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması. Bilişim Teknolojileri Dergisi, 10(3), 319-326. Kaynar, O., Görmez, Y., ve Işık, Y. E. (2016). Oto Kodlayıcı Tabanlı Derin Öğrenme Makinaları ile Spam Tespiti. Paper presented at the 3. Uluslararası Yönetim Bilişim Konferansı, İzmir.
  • Lewis, N. D. C. (2016). Deep Learning Made Easy with R: A Gentle Introduction for Data Science. California: CreateSpace Independent Publishing Platform.
  • Liu, G., Bao, H., ve Han, B. (2018). A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis. Mathematical Problems in Engineering, 2018. Liu, H. (2018). Leveraging Financial News for Stock Trend Prediction with Attention-Based Recurrent Neural Network. arXiv preprint arXiv:.06173, 1-24. Mosavi, A., Ozturk, P., ve Chau, K.-w. (2018). Flood Prediction Using Machine Learning Models: Literature Review. Water, 10(11), 1536. doi:10.3390/w10111536
  • Öner, İ. V., Yeşilyurt, M. K., ve Yılmaz, E. Ç. (2017). Wavelet Analiz Tekniği ve Uygulama Alanları. Ordu Üniversitesi Bilim ve Teknoloji Dergisi, 7(1), 42-56.
  • Qi, Y., Shen, C., Liu, J., Li, X., Li, D., ve Zhu, Z. (2017). An Automatic Feature Learning and Fault Diagnosis Method Based on Stacked Sparse Autoencoder. Paper presented at the International Workshop of Advanced Manufacturing and Automation.
  • Ramsey, J. B. (2002). Wavelets in Economics and Finance: Past and Future. Studies in Nonlinear Dynamics & Econometrics, 6(3).
  • Selvin, S., Vinayakumar, R., Gopalakrishnan, E. A., Menon, V. K., ve Soman, K. P. (2017). Stock Price Prediction Using LSTM, RNN and CNN-sliding Window Model. Paper presented at the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).
  • Sim, H. S., Kim, H. I., ve Ahn, J. J. (2019). Is Deep Learning for Image Recognition Applicable to Stock Market Prediction? Complexity, 2019, 1-10. doi:10.1155/2019/4324878
  • Singh, D., Merdivan, E., Psychoula, I., Kropf, J., Hanke, S., Geist, M., ve Holzinger, A. (2017). Human Activity Recognition Using Recurrent Neural Networks. Paper presented at the International Cross-Domain Conference for Machine Learning and Knowledge Extraction.
  • Şeker, A., Diri, B., ve Balık, H. H. (2017). Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme. Gazi Mühendislik Bilimleri Dergisi, 3(3), 47-64.
  • Tokgöz, A., ve Ünal, G. (2018). A RNN based time series approach for forecasting turkish electricity load. Paper presented at the 2018 26th Signal Processing and Communications Applications Conference (SIU).
  • Toprak, İ. B., Çağlar, M. F., ve Merdan, M. (2007). Ayrık Dalgacık Dönüşümü ve Yapay Sinir Ağları Kullanarak EEG Sinyallerinden Otomatik Epilepsi Teşhisi. Paper presented at the IEEE 15.Sinyal İşleme ve İletişim Uygulamaları Kurultayı, Eskişehir.
  • Ugwu, C., ve OnwuachuUzochukwu, C. (2014). Machine Learning Application for Stock Market Prices Prediction. IOSR Journal of Computer Engineering, 16(5), 112-122.
  • Vasilev, I., Slater, D., Spacagna, G., Roelants, P., ve Zocca, V. (2019). Python Deep Learning (2. b.). Birmingham: Packt Publishing.
  • Wang, Z., Hu, J., ve Wu, Y. (2018). A Bimodel Algorithm with Data-Divider to Predict Stock Index. Mathematical Problems in Engineering, 1-14. doi:10.1155/2018/3967525
  • Wani, M. A., Bhat, F. A., Afzal, S., ve Khan, A. I. (2020). Studies in Big Data (Vol. 57). Singapore: Springer.

XU30 INDEX PREDICTION WITH DEEP LEARNING ARCHITECTURES

Year 2019, Volume: 4 Issue: 2, 106 - 121, 29.10.2019

Abstract

Deep
learning methods can automatically detect and analyze to complex patterns of
data and interactions between data in order to expedite to process and ensure
accuracy in the processing steps. Implementation of deep learning methods in
the finance area will be useful in meeting the need to reach information as
quickly and accurately as possible. Furthermore, through the use of these
methods, the solution of financial forecasting problems such as the design and
pricing of mutual funds, the creation of the optimal portfolio and the
realization of financial risk management, which involve big and complex data
sets, will be facilitated. This study aims to obtain the daily movement
forecast of XU30 Index with the deep learning architecture.

References

  • Aslan, S., Badem, H., Özcan, T., Karaboğa, D., ve Baştürk, A. (2015). Çoklu Ekran Kartı ile Hızlandırılmış Ayrık Haar Dalgacık Dönüşümü Temelli Görüntü Şıkıştırma. Kahramanmaras Sutcu Imam University Journal of Engineering Sciences, 18(2), 12-16.
  • Buduma, N., ve Locascio, N. (2017). Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms. Boston: O'Reilly Media, Inc.
  • Canyılmaz, M., Türk, M., ve Güzel, E. (2016). Uzaktan Algılanan Düşük Frekanslı Sinyallerin Gürültülerinin Giderilmesinde Dalgacık Dönüşümü Ailelerinin Performanslarının İncelenmesi ve Karşılaştırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 73-77.
  • Chung, H., ve Shin, K.-s. (2018). Genetic algorithm-optimized long short-term memory network for stock market prediction. Sustainability, 10(10), 3765-3782. doi:10.3390/su10103765
  • Ciaburro, G., ve Venkateswaran, B. (2017). Neural Networks with R: Smart models using CNN, RNN, deep learning, and artificial intelligence principles. Birmingham: Packt Publishing Ltd.
  • Çalişan, M., ve Talu, M. F. (2017). Examination of the Effect of the Basic parameters of the Auto-encoder on Coding Performance. Paper presented at the 2017 International Artificial Intelligence and Data Processing Symposium (IDAP).
  • Derbeko, P., Dolev, S., ve Gudes, E. (2018). Privacy via Maintaining Small Similitude Data for Big Data Statistical Representation. Paper presented at the International Symposium on Cyber Security Cryptography and Machine Learning, Beer Sheva, Israel.
  • Erdogan, H., Hershey, J. R., Watanabe, S., ve Le Roux, J. (2017). Deep Recurrent Networks for Separation and Recognition of Single-Channel Speech in Nonstationary Background Audio. In New Era for Robust Speech Recognition (ss. 165-186): Springer.
  • Gurjar, M., Naik, P., Mujumdar, G., ve Vaidya, T. (2018). Stock Market Prediction Using ANN. International Research Journal of Engineering and Technology, 5(3), 2758-2761.
  • Heaton, J. (2015). Artificial Intelligence for Humans, Volume 3: Neural Networks and Deep Learning (Vol. 3). Chesterfield: Heaton Research, Inc.
  • Heaton, J. B., Polson, N. G., ve Witte, J. H. (2017). Deep Learning for Finance: Deep Portfolios. Applied Stochastic Models in Business Industry, 33(1), 3-12.
  • Hsieh, T.-J., Hsiao, H.-F., ve Yeh, W.-C. (2011). Forecasting Stock Markets Using Wavelet Transforms and Recurrent Neural Networks: An Integrated System Based on Artificial Bee Colony Algorithm. Applied soft computing, 11(2), 2510-2525.
  • Kannadasan, K., Edla, D. R., ve Kuppili, V. (2018). Type 2 Diabetes Data Classification Using Stacked Autoencoders in Deep Neural Networks. Clinical Epidemiology Global Health.
  • Kaynar, O., Aydın, Z., ve Görmez, Y. (2017). Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması. Bilişim Teknolojileri Dergisi, 10(3), 319-326. Kaynar, O., Görmez, Y., ve Işık, Y. E. (2016). Oto Kodlayıcı Tabanlı Derin Öğrenme Makinaları ile Spam Tespiti. Paper presented at the 3. Uluslararası Yönetim Bilişim Konferansı, İzmir.
  • Lewis, N. D. C. (2016). Deep Learning Made Easy with R: A Gentle Introduction for Data Science. California: CreateSpace Independent Publishing Platform.
  • Liu, G., Bao, H., ve Han, B. (2018). A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis. Mathematical Problems in Engineering, 2018. Liu, H. (2018). Leveraging Financial News for Stock Trend Prediction with Attention-Based Recurrent Neural Network. arXiv preprint arXiv:.06173, 1-24. Mosavi, A., Ozturk, P., ve Chau, K.-w. (2018). Flood Prediction Using Machine Learning Models: Literature Review. Water, 10(11), 1536. doi:10.3390/w10111536
  • Öner, İ. V., Yeşilyurt, M. K., ve Yılmaz, E. Ç. (2017). Wavelet Analiz Tekniği ve Uygulama Alanları. Ordu Üniversitesi Bilim ve Teknoloji Dergisi, 7(1), 42-56.
  • Qi, Y., Shen, C., Liu, J., Li, X., Li, D., ve Zhu, Z. (2017). An Automatic Feature Learning and Fault Diagnosis Method Based on Stacked Sparse Autoencoder. Paper presented at the International Workshop of Advanced Manufacturing and Automation.
  • Ramsey, J. B. (2002). Wavelets in Economics and Finance: Past and Future. Studies in Nonlinear Dynamics & Econometrics, 6(3).
  • Selvin, S., Vinayakumar, R., Gopalakrishnan, E. A., Menon, V. K., ve Soman, K. P. (2017). Stock Price Prediction Using LSTM, RNN and CNN-sliding Window Model. Paper presented at the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).
  • Sim, H. S., Kim, H. I., ve Ahn, J. J. (2019). Is Deep Learning for Image Recognition Applicable to Stock Market Prediction? Complexity, 2019, 1-10. doi:10.1155/2019/4324878
  • Singh, D., Merdivan, E., Psychoula, I., Kropf, J., Hanke, S., Geist, M., ve Holzinger, A. (2017). Human Activity Recognition Using Recurrent Neural Networks. Paper presented at the International Cross-Domain Conference for Machine Learning and Knowledge Extraction.
  • Şeker, A., Diri, B., ve Balık, H. H. (2017). Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme. Gazi Mühendislik Bilimleri Dergisi, 3(3), 47-64.
  • Tokgöz, A., ve Ünal, G. (2018). A RNN based time series approach for forecasting turkish electricity load. Paper presented at the 2018 26th Signal Processing and Communications Applications Conference (SIU).
  • Toprak, İ. B., Çağlar, M. F., ve Merdan, M. (2007). Ayrık Dalgacık Dönüşümü ve Yapay Sinir Ağları Kullanarak EEG Sinyallerinden Otomatik Epilepsi Teşhisi. Paper presented at the IEEE 15.Sinyal İşleme ve İletişim Uygulamaları Kurultayı, Eskişehir.
  • Ugwu, C., ve OnwuachuUzochukwu, C. (2014). Machine Learning Application for Stock Market Prices Prediction. IOSR Journal of Computer Engineering, 16(5), 112-122.
  • Vasilev, I., Slater, D., Spacagna, G., Roelants, P., ve Zocca, V. (2019). Python Deep Learning (2. b.). Birmingham: Packt Publishing.
  • Wang, Z., Hu, J., ve Wu, Y. (2018). A Bimodel Algorithm with Data-Divider to Predict Stock Index. Mathematical Problems in Engineering, 1-14. doi:10.1155/2018/3967525
  • Wani, M. A., Bhat, F. A., Afzal, S., ve Khan, A. I. (2020). Studies in Big Data (Vol. 57). Singapore: Springer.
There are 29 citations in total.

Details

Primary Language Turkish
Journal Section Articles
Authors

Şakir Sakarya

Ümit Yılmaz

Publication Date October 29, 2019
Published in Issue Year 2019 Volume: 4 Issue: 2

Cite

APA Sakarya, Ş., & Yılmaz, Ü. (2019). Derin Öğrenme Mimarisi Kullanarak BİST30 İndeksinin Tahmini. European Journal of Educational and Social Sciences, 4(2), 106-121.