Uzun Kısa Vadeli Bellek Tekrarlayan Sinir Ağı Kullanarak Bitcoin Kripto Para Birimi Fiyat Tahmini

Year 2022, , 47 - 53, 31.08.2022

Ahmad Bilal Wardak Jawad Rasheed

https://doi.org/10.31590/ejosat.1079622

Abstract

Artan popülaritesi ve ticari kabulü nedeniyle, kripto para birimi finansal sistemi değiştirmede giderek daha önemli bir rol oynamaktadır. Birçok kişi kripto para birimine yatırım yaparken, kripto para biriminin dinamik özellikleri ve öngörülebilirliği hala büyük ölçüde bilinmemektedir ve bu da yatırımları riske sokmaktadır. Bu yazıda, Tekrarlayan Sinir Ağını (LSTM) kullanarak değerini mümkün olan en yüksek doğrulukla etkileyen çeşitli faktörleri dikkate alarak Bitcoin fiyatını tahmin etmeye çalışıyoruz. Bu çalışmada kullandığımız veriler, beş yıllık bir süre boyunca Bitcoin fiyatlandırmasının birçok yönünün güncellenmiş günlük kayıtlarını içermektedir. Kripto para birimi (Bitcoin) verileri çok değişken olduğundan, daha iyi bir tahmin sonucuna sahip olmak için verilerin etkili bir ön işlemesini uyguluyoruz. Bu çözümle %95.7'lik bir doğruluk ve 0.05'lik bir RMSE elde ediyoruz. Ayrıca, bu çalışmayı performans ve doğruluğa dayalı olarak mevcut diğer yöntemlerle karşılaştırıyoruz. Bu karşılaştırma, LSTM'yi yeterli hiperparametre ayarlaması ile kullanmanın, kripto para birimi fiyat tahmini için en etkili yollardan biri olduğunu göstermektedir.

Keywords

Kripto para, Bitcoin, blok zinciri, Nöral Ağlar, Derin Öğrenme

Bitcoin Cryptocurrency Price Prediction Using Long Short-Term Memory Recurrent Neural Network

Abstract

Due to its growing popularity and commercial acceptance, cryptocurrency is playing an increasingly essential role in altering the financial system. While many people are investing in cryptocurrency, the dynamic characteristics and predictability of cryptocurrency are still largely unknown, putting investments at risk. In this paper, we attempt to anticipate the Bitcoin price by taking into account a variety of factors that influence its value with the highest possible accuracy using (LSTM) Recurrent Neural Network. The data we use in this work includes updated daily records of many aspects of Bitcoin pricing over a five-year period. Since the cryptocurrency (Bitcoin) data is so volatile, we implement an effective pre-processing of the data in order to have a better prediction result. With this solution, we gain accuracy of 95.7% and RMSE of 0.05. Furthermore, we compare this work with other existing methods based on performance and accuracy. This comparison demonstrates that utilizing LSTM with adequate hyperparameter tweaking is one of the most efficient ways for cryptocurrency price prediction.

Keywords

Cryptocurrency, Bitcoin, Blockchain, Neural Networks, Deep Learning, RNN, LSTM

References

• A. Canziani, Adam Paszke, E. C. (2016). An Analysis of Deep Neural Network Models for Practical Applications. ArXiv, abs/1605.0.
• Albariqi, R., & Winarko, E. (2020). Prediction of Bitcoin Price Change using Neural Networks. Proceeding - ICoSTA 2020: 2020 International Conference on Smart Technology and Applications: Empowering Industrial IoT by Implementing Green Technology for Sustainable Development, 1–4. https://doi.org/10.1109/ICoSTA48221.2020.1570610936
• Alkaya, A. (2013). NEURON OPTIMIZATION OF EVOLUTIONARY ARTIFICIAL NEURAL NETWORKS FOR STOCK PRICE INDEX PREDICTION. International Journal of Economics and Finance Studies, 5 (1), 12–21. https://dergipark.org.tr/en/pub/ijefs/issue/26160/2
• Bitstamp. (2022). Bitcoin BTC/USD. https://www.bitstamp.net
• CryptoCompare. (n.d.). The Premium API Solution. https://min-api.cryptocompare.com
• Ferdiansyah, Othman, S. H., Zahilah Raja Md Radzi, R., Stiawan, D., Sazaki, Y., & Ependi, U. (2019). A LSTM-Method for Bitcoin Price Prediction: A Case Study Yahoo Finance Stock Market. ICECOS 2019 - 3rd International Conference on Electrical Engineering and Computer Science, Proceeding, June, 206–210. https://doi.org/10.1109/ICECOS47637.2019.8984499
• Greenberg, A. (2011). Crypto Currency. https://www.forbes.com/forbes/2011/0509/technology-psilocybin-bitcoins-gavin-andresen-crypto-currency.html?sh=7906850a353e
• Haagsman, E. (2019). Collaboration with Anaconda, Inc. PyCharm Blog.
• JetBrains Strikes Python Developers with PyCharm 1.0 IDE. (n.d.). https://www.eweek.com/development/jetbrains-strikes-python-developers-with-pycharm-1.0-ide
• Kanagachidambaresan, K. B. P. R. R. (2021). Introduction to Tensorflow Package. Programming with TensorFlow, 1–4.
• Kemalbay G., B. K. O. (2021). SARIMA-ARCH versus genetic programming in stock price prediction. Sigma Journal of Engineering and Natural Sciences, 39(2), 110–122.
• Kharpal, A. (2018). Everything you need to know about the blockchain.
• Lahmiri, S., & Bekiros, S. (2021). Deep Learning Forecasting in Cryptocurrency High-Frequency Trading. Cognitive Computation, 13(2), 485–487. https://doi.org/10.1007/s12559-021-09841-w
• McNally, S., Roche, J., & Caton, S. (2018). Predicting the Price of Bitcoin Using Machine Learning. Proceedings - 26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018, 339–343. https://doi.org/10.1109/PDP2018.2018.00060
• Patel, M. M., Tanwar, S., Gupta, R., & Kumar, N. (2020). A Deep Learning-based Cryptocurrency Price Prediction Scheme for Financial Institutions. Journal of Information Security and Applications, 55(May), 102583. https://doi.org/10.1016/j.jisa.2020.102583
• Rasheed, J., Jamil, A., Ali Hameed, A., Ilyas, M., Ozyavas, A., & Ajlouni, N. (2020). Improving Stock Prediction Accuracy Using CNN and LSTM. 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020. https://doi.org/10.1109/ICDABI51230.2020.9325597
• Raşo, H. & Demirci, M. (2019). Predicting the Turkish Stock Market BIST 30 Index using Deep Learning. International Journal of Engineering Research and Development, 11 (1), 253–265. doi: 10.29137/umagd.425560
• Sebastião, H., & Godinho, P. (2021). Forecasting and trading cryptocurrencies with machine learning under changing market conditions. Financial Innovation, 7(1). https://doi.org/10.1186/s40854-020-00217-x
• Sepp Hochreiter, J. S. (1997). Long Short-Term Memory. Neural Computation, 9 (8), 1735–1780. https://doi.org/https://doi.org/10.1162/neco.1997.9.8.1735
• Singh, V. (2017). Basic Architecture of RNN and LSTM.
• Th15 Week ’ s Citation Classic ®. (1989). 1970, 1989.
• Vigna Paul, C. M. J. (2016). The Age of Cryptocurrency: How Bitcoin and the Blockchain Are Challenging the Global Economic Order.