Journals / Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty / 2026 / Volume: 10 Issue: 1

PREDICTION OF CRYPTO MONEY PRICES WITH LSTM AND GRU MODELS

KRİPTO PARA FİYATLARININ LSTM VE GRU MODELLERİ İLE TAHMİNİ

Esranur Demirci(SAMSUN ÜNİVERSİTESİ)0000-0002-7840-2398
Meltem Karaatlı(SÜLEYMAN DEMİREL ÜNİVERSİTESİ)0000-0002-7403-9587
Pages
—
Publication Date
2023-03-29
🏛️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)

When the methods used were compared, the best estimation result was reached with the GRU model for Bitcoin and Ripple, and the LSTM model for Ethereum, according to the MAPE performance criterion.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Cryptocurrencies, which entered our lives in the recent past and found a place in the financial markets in a short time, are used both as a means of exchange and an investment tool.
📊
Key Findings & Data:For this reason, in this study, a 30-day price estimate of Bitcoin, Ethereum and Ripple, which are the crypto currencies with the highest market value and transaction volume, has been made using LSTM and GRU, a special RNN method.
💡
Conclusion & Impact:When the methods used were compared, the best estimation result was reached with the GRU model for Bitcoin and Ripple, and the LSTM model for Ethereum, according to the MAPE performance criterion.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Crypto-Currency · Bitcoin · Ethereum

Abstract

Cryptocurrencies, which entered our lives in the recent past and found a place in the financial markets in a short time, are used both as a means of exchange and an investment tool. The fact that cryptocurrencies are not under the control of a central authority has brought about fluctuations in the prices of these vehicles. Therefore, the development of an intelligent forecasting model is very important for the selection of financial assets to be invested and the realization of investment decisions. Deep learning and artificial intelligence are used in the selection of cryptocurrency and other investment instruments to be invested. Deep learning models such as the Recurrent Neural Network (RNN), Long-Short Term Memory (LSTM) and the Gated Recurrent Unit (GRU) model have been proven by researchers to outperform traditional time series models in cryptocurrency price prediction. For this reason, in this study, a 30-day price estimate of Bitcoin, Ethereum and Ripple, which are the crypto currencies with the highest market value and transaction volume, has been made using LSTM and GRU, a special RNN method. As a result of the research, Bitcoin gave the best prediction result in both models. The second best prediction result was found for Ripple, then Ethereum. When the methods used were compared, the best estimation result was reached with the GRU model for Bitcoin and Ripple, and the LSTM model for Ethereum, according to the MAPE performance criterion.

Özet

Yakın geçmişte hayatımıza giren ve kısa zamanda finansal piyasalarda kendisine yer bulan kripto paralar, hem bir değişim aracı hem de bir yatırım aracı olarak kullanılmaktadır. Kripto paraların merkezi bir otoritenin kontrolünde olmaması bu araçların fiyatlarında dalgalanmaları beraberinde getirmiştir. Bu nedenle, akıllı bir tahmin modelinin geliştirilmesi, yatırım yapılacak finansal varlıkların seçimi ve yatırım kararlarının hayata geçirilmesi açısından oldukça önemlidir. Derin öğrenme ve yapay zeka, yatırım yapılacak olan kripto para birimi ve diğer yatırım araçlarının seçiminde kullanılmaktadır. Tekrarlayan Sinir Ağı (RNN), Uzun-Kısa Süreli Bellek (LSTM) ve Geçitli Yinelenen Birim (GRU) modeli gibi derin öğrenme modellerinin, kripto para birimi fiyat tahmininde geleneksel zaman serisi modellerinden daha iyi performans gösterdiği araştırmacılar tarafından kanıtlanmıştır. Bundan dolayı bu çalışmada, özel bir RNN yöntemi olan LSTM ve GRU’dan yararlanılarak, günümüzde piyasa değeri ve işlem hacmi en yüksek olan kripto paralardan Bitcoin, Ethereum ve Ripple’ın 30 günlük fiyat tahmininde bulunulmuştur. Araştırmanın sonucunda her iki modelde de en iyi tahmin sonucunu Bitcoin vermiştir. İkinci en iyi tahmin sonucu Ripple, sonrasında ise Ethereum için bulunmuştur. Kullanılan yöntemler karşılaştırıldığında ise MAPE performans ölçütüne göre en iyi tahmin sonucuna Bitcoin ve Ripple için GRU, Ethereum için ise LSTM modeli ile ulaşılmıştır.

🔖

Cite This Article

Demirci, E., Karaatlı, M. (2023). PREDICTION OF CRYPTO MONEY PRICES WITH LSTM AND GRU MODELS. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, Volume: 10 Issue: 1. https://doi.org/10.30798/makuiibf.1035314

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (56)

  1. Avrupa Merkez Bankası. (2020, Eylül). US Dollar (USD). Erişim adresi https://www.ecb.europa.eu/stats/policy_and_exchange_rates/euro_reference_exchange_rates/html/usd.xml
  2. BtcTurk. (2013). Bitcoin (BTC) Nedir?. Erişim adresi https://www.btcturk.com/bilgi-platformu/bitcoin-btc-nedir/
  3. Buterin, V. (2014). A Next-Generation Smart Contract and Decentralized Application Platform. Erişim adresi https://github.com/ethereum/wiki/wiki/White-Paper
  4. Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, June 3.
  5. Coin Medya. (2020). Ethereum Nedir?. Erişim adresi https://btc.coinmedya.com/ethereum-nedir.html
  6. CoinMarketCap. (2020, Aralık). About Bitcoin. Erişim adresi https://coinmarketcap.com/tr/currencies/bitcoin/
  7. CoinMarketCap. (2020, Aralık). About Ethereum. Erişim adresi https://coinmarketcap.com/currencies/ethereum/
  8. CoinMarketCap. (2020, Eylül). About XRP. Erişim adresi https://coinmarketcap.com/tr/currencies/xrp/
  9. CoinMarketCap. (2020, Eylül). Bitcoin Volume. Erişim adresi https://coinmarketcap.com/currencies/bitcoin/historical-data/?start=20130429&end=20200916
  10. CoinMarketCap. (2020, Eylül). Ethereum Volume. Erişim adresi https://coinmarketcap.com/currencies/ethereum/historical-data/?start=20140906&end=20200916
  11. CoinMarketCap. (2020, Eylül). XRP (Ripple) Volume, Erişim adresi https://coinmarketcap.com/currencies/xrp/historical-data/?start=20130429&end=20200916
  12. Coin Metrics. (2020, Eylül). Bitcoin Price (USD) and Supply, Free Float. Erişim adresi https://coinmetrics.io/tools/
  13. Coin Metrics. (2020, Eylül). Ethereum Price (USD) and Supply, Free Float. Erişim adresi https://coinmetrics.io/tools/
  14. Coin Metrics. (2020, Eylül). XRP(Ripple) Price (USD) and Supply, Free Float. Erişim adresi https://coinmetrics.io/tools/
  15. Colah’s Blog. (2015). Understanding LSTM Networks. Erişim adresi http://colah.github.io/posts/2015-08-Understanding-LSTMs/
  16. Çetinkaya, Ş. (2018). Kripto paraların gelişimi ve para piyasalarındaki yerinin Swot Analizi ile incelenmesi. Uluslararası Ekonomi ve Siyaset Bilimleri Akademik Araştırmalar Dergisi, 2 (5), 11-21.
  17. Demir, E., Gozgora, G., Lao, C.K.M. ve Vigne, S.A. (2018). Does economic policy uncertainty predict the bitcoin returns?. An Empirical Investigation, Finance Research Letters, 26, 145-149. https://doi.org/10.1016/j.frl.2018.01.005
  18. Deng, L. ve Yu, D. (2014). Deep learning: Methods and applications. Found. Trends® Signal Process, 7(3–4), 197–387. DOI: 10.1561/2000000039
  19. Dutta, A., Kumar, S. ve Baus, M. (2020). A Gated Recurrent Unit Approach to Bitcoin Price Prediction. Journal of Risk and Financial Management, 13(2), 1-16. DOI: 10.3390/jrfm13020023
  20. Economic Policy Uncertainty. (2020, Kasım). US Equity Market Volatility Index (Financial Crises EMV Tracker). Erişim adresi https://www.policyuncertainty.com/categorical_epu.html
  21. Economic Policy Uncertainty. (2020, Kasım). Monetary Policy Uncertainty Indices (Economic Policy Uncertainty). Erişim adresi https://www.policyuncertainty.com/categorical_epu.html
  22. Economic Policy Uncertainty. (2020, Kasım). Geopolitical Risk Index. Erişim adresi https://www.policyuncertainty.com/gpr.html
  23. Economic Policy Uncertainty. (2020, Kasım). Twitter-Based Uncertainty Indices. Erişim adresi https://www.policyuncertainty.com/twitter_uncert.html
  24. Erdoğan, S. ve Dayan, V. (2019). Blockchain economics and financial market innovation. Editors: Umit H. Analysis of Relationship Between International Interest Rates and Cryptocurrency Prices: Case for Bitcoin and LIBOR. Istanbul: Springer.
  25. FRED (Economic Research Federal Reserve Bank of St. Louis). (2020, Eylül). 12-Month London Interbank Offered Rate (LIBOR), Based on U.S. Dollar. Erişim adresi https://fred.stlouisfed.org/series/USD12MD156N
  26. Gullapalli, S. (2018). Learning to predict cryptocurrency price using artificial meural network models of time series. (Yayımlanmamış yüksek lisans tezi). Department of Computer Science College of Engineering, Master Thesis, Kansas State University, Manhattan, Kansas.
  27. Gruber, N. ve Jockisch, A. (2020). Are GRU cells more specific and LSTM cells more sensitive in motive classification of text?. Frontiers in Artificial Intelligence, 3, 1-6. https://doi.org/10.3389/frai.2020.00040
  28. Günen, E. (2020). Bitcoin'in Piyasa Değeri 30 Saatte 11 Milyar Dolar Arttı. Erişim adresi https://tr.cointelegraph.com/news/bitcoin-market-capitalization-rised-11b-in-30-hours
  29. Gürbüz, F.B. (2020). Tekrarlayan Sinir Ağı-Recurrent Neural Networks (RNN). Erişim adresi https://medium.com/@batincangurbuz/tekrarlayan-sinir-a%C4%9F%C4%B1-recurrent-neural-networks-rnn-17b517dd0b3e
  30. Hayes, A.S. (2017). Cryptocurrency value formation: An empirical study leading to a cost of poduction model for valuing bitcoin. Telematics and Informatics, 34(7), 1308-1321.
  31. Hewlett Packard Enterprise. (2016). Blockchain in the financial services industry. Business White Paper, 61(4), 1-10.
  32. Hirano, Y., Pichl, L., Eom, C. ve Kaizoji, T. (2018). Analysis of Bitcoin market efficiency by using machine learning. In CBU International Conference Proceedings, 6, 175-180. DOI: 10.12955/cbup.v6.1152
  33. Hochreiter, S. ve Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. DOI: 10.1162/neco.1997.9.8.1735
  34. Investing.com. (2020, Eylül). Ham Petrol WTI Vadeli İşlemleri. Erişim adresi https://tr.investing.com/commodities/crude-oil-historical-data
  35. Investing.com. (2020, Eylül). S&P 500. Erişim adresi https://tr.investing.com/indices/us-spx-500-historical-data
  36. Investing.com. (2020, Eylül). XAU/USD-Altın Spot Amerikan Doları. Erişim adresi https://tr.investing.com/currencies/xau-usd-historical-data
  37. Krause, E.G., Velamuri, V.K., Burghardt, T., Nack, D., Schmidt, M. ve Treder, T.M. Blockchain technology and the financial services market State-of-the-Art Analysis. HHL, 6, 2016.
  38. Kostadinov, S. (2017). Understanding GRU Networks. Erişim adresi https://towardsdatascience.com/understanding-gru-networks-2ef37df6c9be
  39. Kristoufek, L. (2015). What are the main drivers of the Bitcoin price?. Evidence from Wavelet Coherence Analysis, Plos One, 10(4), 1-15. https://doi.org/10.1371/journal.pone.0123923
  40. Livieris, I.E., Pintelas, E., Stavroyiannis, S. ve Pintelas, P. (2020). Ensemble deep learning models for forecasting cryptocurrency time-series. Algorithms, 13 (5), 1-21. https://doi.org/10.3390/a13050121
  41. Melih Güney, (2015). Bitcoin Nedir? Bitcoin Nasıl Üretilir?. Erişim adresi https://www.melihguney.com/bitcoin-nedir-nasil-uretilir.html
  42. Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system. 1-9.
  43. Nakano, M., Takahashi, A. ve Takahashi, S. (2018). Bitcoin technical trading with Artificial Neural Network. Physica A: Statistical Mechanics and its Applications, 510, 587-609. https://doi.org/10.1016/j.physa.2018.07.017
  44. Nunes, B.S.R. (2017). Virtual currency: A Cointegration Analysis between Bitcoin prices and economic and financial data. (Yayınlanmış Yüksek Lisans Tezi). ISCTE Business School, Lizbon, 1-88.
  45. Paribulog. (2019). 6 Maddede Ripple (XRP). Erişim adresi https://www.paribu.com/blog/kriptopara/6-maddede-xrp-nedir/
  46. Phi, M. (2018). Illustrated Guide to LSTM’s and GRU’s: A Step by Step Explanation. Erişim adresi https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21
  47. Pisa, M. ve Juden, M. (2017). Blockchain and economic development: Hype vs. reality. Center For Global Development, 107, 1-47.
  48. Polat, A. ve Akbıyık, A. (2019). Sosyal medya ve yatırım araçlarının değeri arasındaki ilişkinin incelenemesi: Bitcoin Örneği. Akademik İncelemeler Dergisi, 14 (1), 443-462. DOI: 10.17550/akademikincelemeler.543486
  49. PricewaterhouseCoopers (PwC). (2017). Building Blocks: How Financial Services Can Create Trust in Blockchain. Erişim adresi https://www.pwc.com/publications/pwc-whitepaper-blockchain-trust.pdf
  50. Ripple. (2020). Ripple. Erişim adresi https://ripple.com/xrp/
  51. Scikit-Learn. (2020). Compare The Effect of Different Scalers on Data with Outlier. Erişim adresi https://scikit-learn.org/stable/auto_examples/preprocessing/plot_all_scaling.html
  52. Spirina, K. (2018). How Artificial Neural Networks Can Code Smarter Than GUI Programmer. Erişim adresi https://hackernoon.com/how-artificial-neural-networks-can-code-smarter-than-gui-programmer-1cdfaecb4851
  53. Stenqvist, E. ve Lönnö, J. (2017). Predicting Bitcoin price fluctuation with twitter Sentiment Analysis. Degree Project in Technology, First Cycle, 15 Credist, 3-31.
  54. Şahin, E.E. (2020). Bitcoin Fiyatına etki eden faktörlerin Mars Metodu ile belirlenmesi. Uluslararası Ekonomi, İşletme ve Politika Dergisi, 4 (1), 171-184.
  55. Weiss, G., Goldberg, Y. ve Yahay, E. (2018). On the Practical Computational Power of Finite Precision RNNs for Language Recognition. arXiv:1805.04908, 2018. Erişim adresi https://arxiv.org/abs/1805.04908
  56. Zoumpekas, T., Houstis, E. ve Vavalos, M. (2020). ETH Analysis and Predictions Utilizing Deep Learning. Expert Systems With Applications, 162, 1-15. https://doi.org/10.1016/j.eswa.2020.113866