With the successfully developed model, it is possible to estimate price for BTC, Ethereum and Ripple with instant data in the future.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:Cryptocurrencies, whose popularity is increasing day by day today, affect the real economy, financial sector and daily life of countries due to the increase in demand and technological developments.
📊
Key Findings & Data:In this study, it is aimed to estimate the value of Bitcoin (BTC), which has the most popular and dominant effect among cryptocurrencies, in Turkish Lira (TL) by using the United States Dollar (USD) / (TL) rate and date attributes and with the model to be created, present a generalized forecast model for other cryptocurrencies.
💡
Conclusion & Impact:With the successfully developed model, it is possible to estimate price for BTC, Ethereum and Ripple with instant data in the future.
Cryptocurrencies, whose popularity is increasing day by day today, affect the real economy, financial sector and daily life of countries due to the increase in demand and technological developments. In this study, it is aimed to estimate the value of Bitcoin (BTC), which has the most popular and dominant effect among cryptocurrencies, in Turkish Lira (TL) by using the United States Dollar (USD) / (TL) rate and date attributes and with the model to be created, present a generalized forecast model for other cryptocurrencies. The data feature used in the study covers the date range of 08.12.2016 and 08.12.2018. The multilayer perceptron techniqueis used for BTC/TL price estimation. As a result of the cross-validation test, estimation results of the multilayer perceptron technique are found to be successful and important. With the successfully developed model, it is possible to estimate price for BTC, Ethereum and Ripple with instant data in the future.
ATLAN, F., PENÇE, İ. (2021). Forecasting Of Bitcoin Price Using The Multilayer Perceptron Technique. Scientific Journal of Mehmet Akif Ersoy University, Cilt: 4 - Sayı: 2, 68–74. https://ajindex.com/articles/799266
Gulli A, Kapoor A, Pal S. (2019). Deep learning with TensorFlow 2 and Keras: Regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API. 2nd ed. Birmingham, United Kingdom, Packt. BITCOIN. “Bitcoin: A peer-to-peer electronic cash system”. https://bitcoin.org/bitcoin.pdf (08.08.2021)
Koçoğlu Ş, Çevik YE, Tanrıöven C. (2016). “Efficiency, Liquidity and Volatility of Bitcoin Markets”. Journal of Business Research, 8(2), 77-97. COINMARKETCAP. ”Indicator about market values of cryptocurrencies”. https://www.coinmarketcap.com (02.08.2021).
Greaves A, Au B. (2015). “Using the bitcoin transaction graph to predict the price of bitcoin”. Department of Computer Science, Stanford University, California, United States of America, Scientific Report, 68. Akcora CG, Dey AK, Gel YR, Kantarcioglu M. (2018). “Forecasting bitcoin price with graph chainlets”. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, Melbourne, Australia. Madan I, Saluja S, Zhao A. (2015). “Automated bitcoin trading via machine learning algorithms”. Department of Computer Science, Stanford University, California, United States of America, Scientific Report, 176. Yang SY, Kim J. (2015). “Bitcoin market return and volatility forecasting using transaction network flow properties”. IEEE 2015 Symposium Series on Computational Intelligence, Cape Town, South Africa, 7-10
December. Matta M, Lunesu I, Marchesı M. (2015). “Bitcoin spread prediction using social and web search media”. The 23rd Conference on User Modelling, Adaptation and Personalization, Dublin, Ireland, 29th June-3rd July. Ceyhan K, Kurtulmaz E, Sert OC, Özyer T. (2018).“Bitcoin movement prediction with text mining”. 2018 26th Signal Processing and Communications Applications Conference (SIU), Cesme, Izmir, 2-5
May. Polat M, Akbıyık A. (2019). “Analyzing The Relationship Between Social Media and Investment Tools: Bıtcoın”. Journal of Academic Inquiries, 14(1), 443-462.
Indera NI, Yassin IM, Zabidi A, Rizman ZI. (2017). “Non-linear autoregressive with exogeneous input (NARX) bitcoin price prediction model using PSO-optimized parameters and moving average technical indicators”. Journal of Fundamental and Applied Sciences, 9(3S), 791-808.