Evaluation of Bitcoin Price Changes Before and After Covid-19 by Machine Learning, Time Series Analysis and Deep Learning Algorithms

Year 2020, Volume: 13 Issue: 3, 341 - 355, 31.07.2020

Uğur Kaya , Fırat Akba , İhsan Medeni Tunç Medeni

https://doi.org/10.17671/gazibtd.648424

Cited By: 3

Abstract

Blockchain technology, which has been become quite widespread in use recently, has become very popular with the Internet technology. Bitcoin, which has been developed with blockchain technology, is the virtual currency that holds the most market volume among virtual currencies. Due to the lack of a central authority that controls the virtual currency markets, this market is open to price manipulations and external interventions, so that guidance is needed for the end-investor to invest. Recently, a number of methods have started to be been used to meet this need.
In this study, various forecasting and classification methods about fluctuation in Bitcoin prices were evaluated together using machine learning, time-series analysis and deep learning methods. In this context, two separate datasets have been created based on the Bitcoin closing prices and up-to-down trends before and after the coronavirus pandemic. The success of forecasting and classification methods on these two datasets were evaluated and compared. As a result of the comparisons, Support Vector Machines method for the study conducted with the data before the pandemic, and ARIMA method for the study conducted with the data after the pandemic, had the most successful results.

Keywords

forecasting, Long-Short Term Memory(LSTM) algorithm, Auto Regressive Integrated Moving Average(ARIMA) method, Support Vector Machines(SVM) algorithm, bitcoin, blockchain technology, cryptocurrency, virtual currency, coronavirus

Covid-19 Öncesi ve Sonrasındaki Bitcoin Fiyat Değişimlerinin Makine Öğrenmesi, Zaman Serileri Analizi ve Derin Öğrenme Yöntemleriyle Değerlendirilmesi

Abstract

Son zamanlarda kullanımı oldukça yaygınlaşan blokzinciri teknolojisinin, İnternet teknolojisi ile beraber adı sıkça anılır olmaya başlamıştır. Blokzinciri teknolojisiyle geliştirilen Bitcoin, sanal para birimleri arasında en çok piyasa hacmini elinde bulunduran sanal para birimidir. Sanal para piyasalarının kontrolünü elinde bulunduran bir merkezi otoritenin olmaması sebebiyle fiyat manipülasyonlarına ve dışarıdan müdahalelere açık olan bu pazarda, en uçtaki yatırımcının yatırım yapabilmesi açısından yol gösterimine ihtiyaç duyulmaktadır. Son zamanlarda bu ihtiyacı karşılamak amacıyla birtakım yöntemler kullanılmaya başlanmıştır. Bu çalışmada makine öğrenmesi, zaman serileri analizi ve derin öğrenme yöntemleri kullanılarak Bitcoin fiyatlarındaki dalgalanma hakkında çeşitli tahminleme ve sınıflama yöntemleri beraber olarak değerlendirilmiştir. Bu bağlamda, koronavirüs pandemisi öncesi ve sonrasındaki Bitcoin kapanış fiyatları ve düşüş-yükseliş eğilimleri baz alınarak iki ayrı veri kümesi oluşturulmuştur. Bu veri kümeleri üzerinde tahmin ve sınıflama yöntemleri değerlendirilerek, başarıları karşılaştırılmıştır. Karşılaştırmalar sonucunda, pandemi öncesi verilerle yapılan çalışmada Destek Vektör Makineleri, pandemi sonrası verilerle yapılan çalışmada ise ARIMA en başarılı sonuçları vermiştir.

Keywords

tahminleme, Uzun Kısa Süreli Bellek Ağları(LSTM) algoritması, Bütünleşik Otoregresif Hareketli Ortalama(ARIMA) yöntemi, Destek Vektör Makineleri(SVM) algoritması, bitcoin, blokzinciri teknolojisi, kriptopara, sanal para, koronavirüs

References

• V. A. Maese, A. W. Avery, B. A.Naftalis, S. P. Wink, Y. D. Valdez, “Cryptocurrency: A Primer”, Banking LJ, 133, 468, 2016.
• Z. Zheng, S. Xie, H. Dai, X. Chen, H. Wang, “An overview of blockchain technology: Architecture, consensus, and future trends”, In 2017 IEEE international congress on big data (BigData congress), 557-564, 2017.
• M. Nofer, P. Gomber, O. Hinz, D. Schiereck, “Blockchain”, Business & Information Systems Engineering, 59(3), 183-187, 2017.
• M. Pilkington, “Blockchain technology: principles and applications”, In Research handbook on digital transformations, 2016.
• M. Tanrıverdi, M. Uysal, M. T. Üstündağ, “Blokzinciri Teknolojisi Nedir? Ne Değildir?: Alanyazın İncelemesi”, Bilişim Teknolojileri Dergisi, 12(3), 203-217, 2019.
• Internet: S. Nakamoto, “Bitcoin: A Peer-to-Peer Electronic Cash System”,http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.9986, 12.11.2019.
• N. Gandal, J.T Hamrick, T. Moore, T. Oberman, “Price manipulation in the Bitcoin ecosystem”, Journal of Monetary Economics, 95, 86-96, 2018.
• Internet: M. Dzirutwe, “Think bitcoin’s getting expensive? Try Zimbabwe”, https://www.reuters.com/article/us-zimbabwe-bitcoin/think-bitcoins-getting-expensive-try-zimbabwe-idUSKBN1DD0NF,27.3.2020.
• J. R. Henrickson, T. L Hogan, W. J. Luther, “The Political Economy of Bitcoin”, Economic Inquiry, 54(2), 925-939, 2016.
• J. Bohr, M. Bashir, “Who uses bitcoin? An Exploration of the Bitcoin Community”, Twelfth Annual International Conference on Privacy, Security and Trust (PST), Toronto, ON, Canada, 94-101, 2014.
• R. Stokes, “Virtual Money Laundering: The case of Bitcoin and the Linden Dollar”, Information & Communications Technology Law, 21(3), 221-236, 2012.
• World Health Organization, Coronavirus disease 2019(COVID-19), Situation Report, 72, 2020.
• Internet: https://tr.cointelegraph.com/news/covid-19-has-reduced-the-risk-of-a-post-halving-price-dump, 02.06.2020.
• S. Savaş, N. Topaloğlu, M. Yılmaz, “Veri Madenciliği ve Türkiye’deki Uygulama Örnekleri”, İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi, 11(21), 1-23, 2012.
• M. Gök, “Maki̇ne Öğrenmesi̇ Yöntemleri̇ i̇le Akademi̇k Başarının Tahmi̇n Edi̇lmesi̇”, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 5(3), 139-148, 2017.
• Y. Peng, P. H. M. Albuquerque, J. M. C. de Sá, A. J. A. Padula, M. R. Montenegro, “The best of two worlds: Forecasting high frequency volatility for cryptocurrencies and traditional currencies with Support Vector Regression”, Expert Systems with Applications, 97, 177-192, 2018.
• H. Jang, J. Lee, “An Empirical Study on Modeling and Prediction of Bitcoin Prices with Bayesian Neural Networks Based on Blockchain I”, IEEE Access, 6, 5427–5437, 2018.
• P. Katsiampa(2017), “Volatility Estimation for Bitcoin: A Comparison of GARCH Models”, Economics Letters, 158, 3-6,2017.
• D. U. Sutiksno, A. S. Ahmar, N. Kurniasih, E. Susanto, A. Leiwakabessy, “Forecasting Historical Data of Bitcoin using ARIMA and α-Sutte Indicator”, Journal of Physics: Conference Series, 1028(1), 012194, 2018.
• N. A. Bakar, S. Rosbi, “Autoregressive Integrated Moving Average (ARIMA) Model for Forecasting Cryptocurrency Exchange Rate in High Volatility Environment: A New Insight of Bitcoin Transaction”, International Journal of Advanced Engineering Research and Science, 4(11), 130-137, 2017.
• E. Ş. Karakoyun, A.O. Çibikdiken, “Comparison of ARIMA Time Series Model and LSTM Deep Learning Algorithm for Bitcoin Price Forecasting”, The 13th Multidisciplinary Academic Conference (The 13th MAC 2018), Prag, Czech Republic, 171-180, 2018.
• S. McNally, J. Roche, S. Caton, “Predicting the Price of Bitcoin Using Machine Learning”, 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), 339-343, 2018.
• B. Sakız, E. Kutlugün, “Bitcoin Price Forecast via Blockchain Technology and Artificial Intelligence Algorithms”, 26th Signal Processing and Communications Applications Conference (SIU), 1–4, 2018.
• A. Azari, “Bitcoin Price Prediction: An ARIMA Approach”, 2019.
• D. Olvaro-Juarez, E. Huerta-Manzanilla, “Forecasting bitcoin pricing with hybrid models: A review of the literature”, International Journal of Advanced Engineering Research and Science, 6(9), 161-164, 2019.
• A. Greaves, B. Au, “Using the Bitcoin Transaction Graph to Predict the Price of Bitcoin”, 2015.
• J. Almeida, S. Tata, A. Moser, V. Smit, “Bitcoin Prediction using ANN”, Neural Networks, 1-12, 2015.
• N. A. Hitam, A. R. Ismail, “Comparative Performance of Machine Learning Algorithms for Cryptocurrency Forecasting”, Indonesian Journal of Electrical Engineering and Computer Science, 11(3), 1121-1128, 2018.
• İ. Çütcü, Y. Kılıç, “Bi̇tcoi̇n Fi̇yatları i̇le Dolar Kuru Arasındaki İlişki: Yapısal Kırılmalı Zaman Seri̇si̇ Anali̇zi”, Yönetim ve Ekonomi Araştırmaları Dergisi, 16(4), 349-366, 2018.
• A. Sönmez, “Sanal Para Bitcoin”, The Turkish Online Journal of Design, Art and Communication (TOJDAC), 4(3), 1-14, 2014.
• J. M. Griffin, A. Shams, “Is Bitcoin Really Un-Tethered?”, Available at SSRN, 3195066, 2018.
• Internet: http://www.coinmarketcap.com, 29.10.2019.
• Z. A. Farhath, B. Arputhamary, L. Arockiam, "A Survey on ARIMA Forecasting Using Time Series Model", Int. J. Comput. Sci. Mobile Comput., 5, 104-109, 2016.
• K. Pichotta, R. J. Mooney, “Learning Statistical Scripts with LSTM Recurrent Neural Networks”, 30th AAAI Conference on Artificial Intelligence (AAAI-16), 2016.
• S. S. Panigrahi, J. K. Mantri, “Epsilon-SVR and Decision Tree for Stock Market Forecasting”, International Conference on Green Computing & Internet of Things, Greater Noida, Delhi, 761-766, 2015.
• C.F. Lin, S. D. Wang, “Fuzzy Support Vector Machines”, IEEE Transactions on Neural Networks, 13(2), 464-471, 2002.
• V. Jakkula, “Tutorial on Support Vector Machine (SVM)”, School of EECS, Washington State University, 2006.
• P. S. Yu, S. T. Chen, I. F. Chang, “Support vector regression for real-time flood stage forecasting”, Journal of Hydrology, 328(3-4), 704-716, 2016.
• D. Bhatt, P. Aggarwal, P. Bhattacharya, V. Devabhaktuni, “An Enhanced MEMS Error Modeling Approach Based on Nu-Support Vector Regression”, Sensors, 12, 9448-9466, 2012.
• F. Zhang, C. Deb, S. E. Lee, J. Yang, K. W. Shah, “Time Series Forecasting for Building Energy Consumption using Weighted Support Vector Regression with Differential Evolution Optimization Technique”, Energy and Buildings, 126, 94-103, 2016.
• M. Story, R. G. Congalton, “Accuracy Assessment: A User's Perspective”, Photogrammetric Engineering and Remote Sensing, 52(3), 397-399, 1986.
• S. J. Darnell, D. Page, J. C. Mitchell, “An automated decision-tree approach to predicting protein interaction hot spots”, Proteins, 68, 813-823, 2007.
• D. M. W. Powers, “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation”, Journal of Machine Learning Technologies, 2(1), 37-63, 2011.
• P. A. Flach, M. Kull, “Precision-Recall-Gain Curves: PR Analysis Done Right”, Advances in Neural Information Processing Systems, 28, 838-846, 2015.
• U. Khair, H. Fahmi, S. Al Hakim, R. Rahim, “Forecasting error calculation with mean absolute deviation and mean absolute percentage error”, In Journal of Physics: Conference Series, 1(930), 012002, 2017.
• G. Brassington, “Mean absolute error and root mean square error: which is the better metric for assessing model performance?”, In EGU General Assembly Conference Abstracts, 19, 3574, 2017.
• S. Boughorbel, F. Jarray, M. El-Anbari, “Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric”, PloS one, 12(6), 2017.
• M. Abdar, “Using Decision Trees in Data Mining for Predicting Factors Influencing of Heart Disease”, Carpathian Journal of Electronic & Computer Engineering, 8(2), 2015.
• F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel,P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, “Scikit-learn: Machine learning in Python”, Journal of Machine Learning Research (JMLR), 12, 2825–2830, 2011.
• T. E. Oliphant, “A guide to NumPy”, USA: Trelgol Publishing, 1, 85, 2006.
• W. McKinney, “Pandas: a foundational Python library for data analysis and statistics”, Python for High Performance and Scientific Computing, 14(9), 2011.
• M. Abadi., P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S.Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, X. Zheng, “Tensorflow: A System for Large-Scale Machine Learning”, In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 265-283, 2016.