SavedAdd your journal

Journals / Kafkas Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi / 2019 / Cilt: 10 - Sayı: 20

FORECASTING THE CRYPTOCURRENCY PRICE USING THE CLASSICAL AND ARTIFICIAL NEURAL NETWORKS MODELS

KRİPTO PARA FİYATLARININ KLASİK VE YAPAY SİNİR AĞI MODELLERİ İLE TAHMİNİ

SERKAN ARAS
Pages
608–640
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)

Among these random walk-dominated series, the best results are obtained with Bitcoin, which is the most widely known and has the highest trading volume, compared with other cryptocurrencies in the study.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Cryptocurrencies are increasing in importance.
📊
Key Findings & Data:Predicting cryptocurrencies as accurately as possible is of great importance for investors and decision makers.
💡
Conclusion & Impact:Among these random walk-dominated series, the best results are obtained with Bitcoin, which is the most widely known and has the highest trading volume, compared with other cryptocurrencies in the study.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Cryptocurrencies are increasing in importance. While to start with they were used only in virtual reality platforms for games, nowadays they are being used by many institutions and organisations as payment instruments. Against security risks, they are produced by an algorithm called blockchain. Predicting cryptocurrencies as accurately as possible is of great importance for investors and decision makers. In the scope of this study, the prices of the most-used four cryptocurrencies (Bitcoin, Ethereum, Ripple, Litecoin) are forecast. The analysis conducted is expanded by determining the break points of each series under investigation via the multiple break point test. For the purpose of predicting the concerned series, both classical time series models and three different artificial neural networks models are employed. In addition, the combining methods are carried out to improve the results. Among these random walk-dominated series, the best results are obtained with Bitcoin, which is the most widely known and has the highest trading volume, compared with other cryptocurrencies in the study.

Özet

Günümüzde kripto para birimlerinin önemi gittikçe artmaktadır. Kripto para birimleri sanal oyun platformlarında kullanılırken, şu an pek çok kurum ve kuruluş tarafından ödeme aracı olarak kullanılmaktadır. Güvenlik risklerine karşı blockchain (Blok Zinciri) adı verilen algoritması ile üretimi sağlanmaktadır. Kripto para fiyatlarının doğru olarak tahmin edilmesi yatırımcı ve karar vericiler açısından büyük önem taşımaktadır. Bu çalışma kapsamında en çok kullanılan dört kripto para birimine (Bitcoin, Ethereum, Ripple, Litecoin) ait fiyat değerleri tahmin edilmiştir. Çoklu kırılma testinden yararlanılarak her seriye ait kırılmalar belirlenerek analiz genişletilmiştir. Ele alınan sanal para değerlerini doğru bir şekilde tahmin etmek amacıyla hem klasik zaman serisi modellerinden hem de üç farklı tür yapay sinir ağı modelinden faydalanılmıştır. Ayrıca elde edilen tahminler üzerinde basit birleştirilme teknikleri uygulanmıştır. Rassal yürüyüşün egemen olduğu bu seriler arasından, özellikle işlem hacmi ve bilinilirliği en fazla olan Bitcoin sanal parasında rassal yürüyüş modelinden daha iyi sonuçlar elde edildiği gözlemlenmiştir.

🔖

Cite This Article

ARAS, S. (2019). FORECASTING THE CRYPTOCURRENCY PRICE USING THE CLASSICAL AND ARTIFICIAL NEURAL NETWORKS MODELS. Kafkas Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, Cilt: 10 - Sayı: 20, 608–640. https://ajindex.com/articles/192883

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (15)

  1. Alessandretti, L., ElBahrawy, A., Aiello, L. M., & Baronchelli, A. (2018). Anticipating cryptocurrency prices using machine learning. Complexity, 2018.
  2. Almeida, J., Tata, S., Moser, A., & Smit, V. (2015). Bitcoin prediciton using ANN. Neural networks, 1-12.
  3. Andrews, D. W. (1993). Tests for parameter instability and structural change with unknown change point. Econometrica: Journal of the Econometric Society, 61(4),821-856.
  4. Andrews, D. W., & Ploberger, W. (1994). Optimal tests when a nuisance parameter is present only under the alternative. Econometrica: Journal of the Econometric Society, 62(6), 1383-1414.
  5. Aras, S., & Gülay, E. (2017). A new consensus between the mean and median combination methods to improve forecasting accuracy. Serbian Journal of Management, 12(2), 217-236.
  6. Aras, S., & Kocakoç, İ. D. (2016). A new model selection strategy in time series forecasting with artificial neural networks: IHTS. Neurocomputing, 174, 974-987.
  7. Aras, S., Deveci Kocakoç, İ., & Polat, C. (2017). Comparative study on retail sales forecasting between single and combination methods. Journal of Business Economics and Management, 18(5), 803-832.
  8. Aras, S., Nguyen, A., White, A., & He, S. (2017). Comparing and Combining MLP and NEAT for Time Series Forecasting. İstanbul Üniversitesi İşletme Fakültesi Dergisi, 46(2), 147-160.
  9. Armstrong, J. S. (Ed.). (2001). Principles of forecasting: a handbook for researchers and practitioners (Vol. 30). Springer Science & Business Media. Baek, C., & Elbeck, M. (2015). Bitcoins as an investment or speculative vehicle? A first look. Applied Economics Letters, 22(1), 30-34.
  10. Bai, J. (1997). Estimating multiple breaks one at a time. Econometric theory, 13(03), 315-352.
  11. Bai, J., & Perron, P. (1998). Estimating and testing linear models with multiple structural changes. Econometrica, 66(1), 47-78.
  12. Bakar, N. A., & Rosbi, S. (2017). High Volatility Detection Method Using Statistical Process Control for Cryptocurrency Exchange Rate: A Case Study of Bitcoin. The International Journal of Engineering and Science, 6(11), 39-48.
  13. Bates, J. M., & Granger, C. W. (1969). The combination of forecasts. Journal of the Operational Research Society, 20(4), 451-468.
  14. Box, G. E. P., & Jenkins, G. (1970).
  15. Time Series Analysis, Forecasting and Control. Holden-Day, San Francisco, CA. Boyacioglu, M. A., & Avci, D. (2010). An adaptive network-based fuzzy inference system (ANFIS) for the prediction of stock market return: the case of the Istanbul stock exchange. Expert Sy