Journals / Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi / 2022 / Cilt: 6 - Sayı: 2

Stock Price Prediction Using Long-Short-Term Memory Network

Uzun-Kısa Süreli Bellek Ağı Kullanarak Hisse Senedi Fiyatı Tahmini

Pages
309–322
Publication Date
2022-09-29
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the test process, consistent and realistic predictions were obtained.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:One of the most important transactions of the financial system is stock trading.
📊
Key Findings & Data:Four stocks within the scope of Borsa İstanbul Technology Index were determined and a 2578-day data set was created between 2012 and 2022, and training and testing was carried out with the established model.
💡
Conclusion & Impact:As a result of the test process, consistent and realistic predictions were obtained.
🔬Design:Modeling & Simulation
📍Scope:2012 Verileri
⚙️Variables:Derin Öğrenme · Uzun-Kısa Süreli Bellek Ağı · Hisse Senedi Fiyatı Tahmini

Abstract

One of the most important transactions of the financial system is stock trading. Stock price data is handle as a financial time series. Stock price predictions using time series analysis are the activity of determining the future value of stocks listed on the stock market. Predicting the price of the stock correctly reduces the risk factor in the decisions to be taken by the investors. Therefore, it is an important issue for the investor. However, because there are many variables that affect the stock price, it is a very complex process to predict. Machine learning methods, especially deep learning algorithms, are frequently used in prediction in the field of finance, as in many other fields. In this study, stock price prediction was made using Long-Short-Term Memory networks, which is one of the deep learning methods. Four stocks within the scope of Borsa İstanbul Technology Index were determined and a 2578-day data set was created between 2012 and 2022, and training and testing was carried out with the established model. As a result of the test process, consistent and realistic predictions were obtained.

Özet

Finans dünyasında hisse senedi ticareti en önemli faaliyetlerden biridir. Hisse senedi verileri finansal bir zaman serisi olarak ele alınmaktadır. Zaman serisi olarak hisse senedi tahmini, bir finansal borsada işlem gören hisse senedinin gelecekteki değerini belirlemeye çalışma eylemidir. Finansal varlıkların fiyatını tahmin etmek, doğru tahminlerle yatırımcıların alacağı kararlarda risk faktörünü azaltabileceğinden önemlidir. Ancak hisse senedi piyasası çok çeşitli faktörlere bağlı olarak değişkenlik gösterdiğinden tahminlemesi zor bir sektör olarak bilinmektedir. Makine öğrenme yöntemleri özellikle de derin öğrenme algoritmaları birçok alanda olduğu gibi finans alanında da tahminlemede sıkça kullanılmaktadır. Bu çalışmada, derin öğrenme yöntemlerinden olan Uzun-Kısa Süreli Bellek ağları kullanarak hisse senedi tahmini yapılmıştır. Borsa İstanbul, Teknoloji Endeksi kapsamındaki dört hisse belirlenerek 2012-2022 yılları arasında 2578 günlük bir veri seti oluşturulmuş ve kurulan model ile eğitim ve test işlemi gerçekleştirilmiştir. Test işlemi sonucunda tutarlı ve gerçeğe yakın tahminler elde edilmiştir.

🔖

Cite This Article

TOKMAK, M. (2022). Stock Price Prediction Using Long-Short-Term Memory Network. Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, Cilt: 6 - Sayı: 2, 309–322. https://ajindex.com/articles/790550

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Aggarwal, D. (2018). Random walk model and asymmetric effect in Korean composite stock price index. Afro-Asian Journal of Finance and Accounting, 8(1), 85-104.
  2. Ahmar, A. S. (2019). Sutte Indicator: an approach to predict the direction of stock market movements. Songklanakarin J. Sci. Technol., 40(5), 1229-1231.
  3. Almasarweh, M., & Alwadi, S. (2018). ARIMA model in predicting banking stock market data. Modern Applied Science, 12(11), 309. Althelaya, K. A., El-Alfy, E.-S. M., & Mohammed, S. (2018). Evaluation of bidirectional LSTM for short-and long-term stock market prediction. 2018 9th international conference on information and communication systems (ICICS), 151-156.
  4. IEEE. Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, e623. doi: 10.7717/peerj-cs.623 Chopra, N. (2019). Time and Frequency Analysis Using the ARMA Model: Evidence from the Indian Stock Market. İçinde Advances in Management Research (ss. 101-114).
  5. CRC Press.
  6. Daver, G., Karacaer, M., & Ünlü, H. (2013). Testing of BIST and TURKDEX: Random walk and market efficiency. International Journal of Economics and Finance Studies, 5(2), 10-22.
  7. Delavar, M., Gholami, A., Shiran, G., Rashidi, Y., Nakhaeizadeh, G., Fedra, K., & Hatefi Afshar, S. (2019). A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran. ISPRS International Journal of Geo-Information, 8(2), 99. doi: 10.3390/ijgi8020099 Elagamy, M. N., Stanier, C., & Sharp, B. (2018). Stock market random forest-text mining system mining critical indicators of stock market movements. 2018 2nd international conference on natural language and speech processing (ICNLSP), 1-8.
  8. IEEE. Fan, J., Li, Q., Hou, J., Feng, X., Karimian, H., & Lin, S. (2017). A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-4/W2, 15-22. doi: 10.5194/isprs-annals-IV-4-W2-15-2017
  9. Google Colaboratory. (2022). Colaboratory. Erişim Tarihi: 10 Ağustos 2022, https://colab.research. google.com/ Gururaj, V., Shriya, V. R., & Ashwini, K. (2019). Stock market prediction using linear regression and support vector machines. Int J Appl Eng Res, 14(8), 1931-1934.
  10. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation