Price Prediction of Bitcoin Using LSTM Neural Network
DOI:
https://doi.org/10.54691/bcpbm.v38i.4183Keywords:
Bitcoin; Price prediction; LSTM; Neural network.Abstract
Contemporarily, cryptocurrency has a high market value, and the price of cryptocurrency fluctuates dramatically. This article analyzes the parameters effects of the LSTM model on Bitcoin price prediction accuracy based on Python and modules of Numpy, Pandas, Keras, Tensorflow, and Sklern. The analysis clarifies the relationship between the accuracy of Bitcoin price prediction and different parameters in the LSTM model. It is discovered that when larger batch sizes are supplied at minor epochs, the accuracy of Bitcoin price prediction declines. Meanwhile, the number of neurons affects the accuracy. In addition, compared to lengths of 14, 30, and 60, the prediction error grows greater when a single time sequence is 7 in length. Apart from that, at present, using closing prices from the past two years rather than the past 1 year, 3 years, or 5 years can make predictions more accurate. These findings shed light on recommendations for adjusting various parameters in the development of the LSTM model for Bitcoin price prediction.
Downloads
References
Nakamoto S. Bitcoin: A peer-to-peer electronic cash system. Decentralized Business Review, 2008: 21260.
Vranken H. Sustainability of bitcoin and blockchains. Current opinion in environmental sustainability, 2017, 28: 1–9.
Nadarajah S, Chu J. On the inefficiency of Bitcoin. Economics Letters, 2017, 150: 6–9.
Böhme R, Christin N, Edelman B, et al. Bitcoin: Economics, technology, and governance. Journal of economic Perspectives, 2015, 29(2): 213-38.
Bitcoin. Investopedia. Retrieved from: https://www.investopedia.com/terms/b/bitcoin.asp.
Binance. Bitcoin. Retrieved from: https://www.binance.com/zh-CN/trade/BTC_BUSD
Huang Y, Duan K, Mishra T. Is Bitcoin really more than a diversifier? A pre-and post-COVID-19 analysis. Finance Research Letters, 2021, 43: 102016.
Chen C, Liu L, Zhao N. Fear sentiment, uncertainty, and bitcoin price dynamics: The case of COVID-19. Emerging Markets Finance and Trade, 2020, 56(10): 2298–2309.
Sarkodie S A, Ahmed M Y, Owusu P A. COVID-19 pandemic improves market signals of cryptocurrencies–evidence from Bitcoin, Bitcoin Cash, Ethereum, and Litecoin. Finance Research Letters, 2022, 44: 102049.
One Of The Biggest Ever Bets On Bitcoin, Worth A Massive $250 Million, Is Already Paying Off. Forbes. Retrieved from: https://www.forbes.com/sites/billybambrough/2020/08/13/one-of-the-biggest-ever-bets-on-bitcoin-worth-a-massive-250-million-is-already-paying-off
Rothschild Investment Corp More Than Tripled Its Bitcoin Position. Nasdaq. Retrieved from: https://www.nasdaq.com/articles/rothschild-investment-corp-more-than-tripled-its-bitcoin-position-2021-07-20.
El Salvador, primer país del mundo en reconocer al Bitcoin como moneda de curso legal. Asamblea. Retrieved from: https://www.asamblea.gob.sv/node/11282.
Goodfellow I, Bengio Y, Courville A. Deep learning (Vol. 1). Cambridge, MIT Press, 2016, pp. 367–415.
Recurrent neural network unfold. Wikimedia. Retrieved from: https://commons.wikimedia.org/wiki/File:Recurrent_neural_network_unfold.svg.
LSTM Cell. Wikimedia. Retrieved from: https://commons.wikimedia.org/wiki/File:LSTM_Cell.svg.
Hochreiter S, Heusel M, Obermayer K. Fast model-based protein homology detection without alignment. Bioinformatics, 2007, 23(14): 1728–1736.
Google claims AI breakthrough machine translation. Wired. Retrieved from: https://www.wired.com/2016/09/google-claims-ai-breakthrough-machine-translation/
Deepminds AI alphastar showcases significant progress towards Agi. Medium. Retrieved from: https://medium.com/@towardai/deepminds-ai-alphastar-showcases-significant-progress-towards-agi-93810c94fbe9
Chen K, Zhou Y, Dai F. A LSTM-based method for stock returns prediction: A case study of China stock market. 2015 IEEE international conference on big data (big data). IEEE, 2015: 2823–2824.
Nelson D M Q, Pereira A C M, de Oliveira R A. Stock market's price movement prediction with LSTM neural networks. 2017 International Joint Conference on Neural Networks (IJCNN), 2017, pp. 1419–1426.
Downloads
Published
Issue
Section
