CRYPTOCURRENCY PREDICTION USING RECURRENT ARTIFICIAL NEURAL NETWORKS
DOI:
https://doi.org/10.47820/recima21.v4i6.3378Keywords:
Bitcoin, Deep Learning, Recurrent Neural Network, Pandas, TensorFlowAbstract
The present study demonstrates the creation of a software that has the ability to predict the oscillation of the Bitcoin cryptocurrency through deep learning and through the recurrent neural network of the Long-Short-Term Memory (LSTM) type, which manipulates the closing values of the cryptocurrency as temporal sequential data. The Software development was based on the Python programming language, using libraries such as Pandas, TensorFlow and Numpy, which are commonly used for data visualization and analysis. The program learning process was based on Bitcoin values in the period from January 2016 to January 2022. After reading the data, the software generated a final prediction graph, which proved to be able to predict the oscillation of a cryptocurrency, despite some divergence of the actual value and the predicted value. It is possible to optimize the software by refining the number of tests performed. However, the results obtained cannot be trusted or used as an investment tool.
Downloads
References
ABADI, M; AGARWAL, A; BARHAM, P et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systens, Estados Unidos, mar. 2016. DOI: https://doi.org/10.48550/arXiv.1603.04467
BISHOP, C, M. Neural Networks for Pattern Recognition. Oxônia: Oxford University Press, 1995, 504p.
BISHOP, C, M. Pattern recognition and machine learning. Nova Iorque: Springer, 2006, 738p.
BRAGA, A; LUDERMIR, T; CARVALHO, A. Redes Neurais Artificiais: Teoria e aplicações. Rio de Janeiro: LTC, 2000, 262p.
FERNANDES, A. Inteligência artificial: noções gerais. Florianópolis: Visual Books, 2003, 160p.
GREFF, K; SRIVASTAVA, R, K; KOUNTNÍK, J et al. LSTM: A Search Space Odyssey. Institute of Electrical and Electronics Engineers, Piscataway, v. 28, n. 10, p. 2222-2232, out. 2017. DOI: https://doi.org/10.48550/arXiv.1503.04069
HARRIS, C; MILLMAN, K; WALT, S et al. Array programming with NumPy, Berlim, v. 585, p 357-362, set. 2020. DOI: https://doi.org/10.1038/s41586-020-2649-2
HAYKIN, S. Neural Networks: A Comprehensive Foundation. Michigan: Pearson, 1998, 842p.
JANIESCH, C; ZSCHECH, P; HEINRICH, K. Machine Learning and Deep Learning. Electronic Markets, Alemanha, v. 31, p 685-695, abr. 2021. DOI: https://doi.org/10.1007/s12525-021-00475-2
KARPATHY, A. The Unreasonable Effectiveness of Recurrent Neural Networks. 2015. Disponível em: <https://karpathy.github.io/2015/05/21/rnn-effectiveness/> Acesso em 20 de mar. 2022.
KOUTNÍK, J; GREFF, K; GOMEZ, F; SCHMIDHUBER, J. A Clockwork RNN. Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):1863-1871, 2014. DOI: https://doi.org/10.48550/arXiv.1402.3511
MATPLOTLIB, 2023. Disponível em: <https://github.com/matplotlib/matplotlib> Acesso em 10 de mar. 2023
MATTOS, O, B; ABOUCHEDID, S; SILVA, L, A. As criptomoedas e os novos desafios ao sistema monetário: uma abordagem pós-keynesiana. Economia e Sociedade, Campinas, v. 29, n. 3, p. 761-778, dez. 2020. DOI: https://doi.org/10.1590/1982-3533.2020v29n3art04
NAKAMOTO, Satoshi. Bitcoin: A Peer-to-Peer Electronic Cash System. 2008. Disponível em: <https://bitcoin.org/bitcoin.pdf> Acesso em 10 de jul. 2022.
NUMPY, Numpy Documentation, 2023. Disponível em: <https://numpy.org/doc/stable/> Acesso em 10 de mar. 2023
PANDAS. Packge Overview, 2023. Disponível em: <https://pandas.pydata.org/docs/getting_started/overview.html> Acesso em 10 de mar. 2023
PEDREGOSA, F; VAROQUAUX, G; GRAMFORT, A et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, Estados Unidos, v. 12, p 2825-2830, 2011
PHI, M. Illustrated Guide to Recurrent Neural Networks. 2018. Disponível em: < https://towardsdatascience.com/illustrated-guide-to-recurrent-neural-networks-79e5eb8049c9> Acesso em 9 de abr. 2022.
ROSA, J. Fundamentos da Inteligência Artificial. Rio de Janeiro: LTC, 2011, 228p.
RUSSEL, S; NORVIG, P. Inteligência Artificial. Rio de Janeiro: Elsevier, 2010, 1136p.
SENA, L; DIAN, M. Criptomoeda: Como obtê-la através da mineração. Revista Interface Tecnológica, Taquaritinga, v.17, n.2, p. 364-375, dez. 2020. DOI: https://doi.org/10.31510/infa.v17i2.1053
SUTSKEVER, I. Training Recurrent Neural Networks. 2013. 101 f. Dissertação (Doutorado em Ciência da Computação) – Universidade de Toronto.
TENSORFLOW, 2023. Disponível em: <https://github.com/tensorflow/tensorflow> Acesso em 10 de mar. 2023
TREDINNICK, L. Cryptocurrencies and the Blockchain. Business Information Review, Reino Unido, v. 36, p 39-44, mar. 2019. DOI: https://doi.org/10.1177/0266382119836314
YFINANCE, 2023. Disponível em: <https://github.com/ranaroussi/yfinance> Acesso em 10 de mar. 2023
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2023 RECIMA21 - Revista Científica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
