Cryptocurrency exchange analysis through the use of artificial intelligence
Keywords:
Artificial intelligence, LSTM, Bitcoin, stock market, cryptocurrencyAbstract
The cryptocurrency exchange market is where it’s possible to buy and sell cryptocurrency like Bitcoin and Ethereum, and where people try to earn money through the price difference between buying and selling, but trying to predict the future value of a currency is hard, and needs a strong mathematical analysis or even a market sentiment analysis to get close to the real value. Thus, this paper’s objective is to use the LSTM (Long short term memory) Deep Learning model, together with techniques of data manipulation like exploratory data analysis, to predict the Bitcoin price and tendency, providing a reliable model that can be used to help traders make decisions on whether or not they should buy a cryptocurrency, aiming at profit. Comparisons were made with previous studies using techniques and models such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).
References
AKITA, Ryo. Deep learning for stock prediction using numerical and textual information. 2016 IEEE/ACIS 15th ICIS, , p. 1–6, 2016.
ALEXANDRE MACEDO, Jose; THEODORO OLIVEIRA CAMARGO, Luis; CESAR BRANDAO DE OLIVEIRA, Humberto; EDUARDO DA SILVA, Luiz; MENEZES SALGADO, Ricardo. An intelligent decision support system to investment in the stock market. IEEE Latin America Transactions, vol. 11, no. 2, p. 812–819, 2013. https://doi.org/10.1109/TLA.2013.6533971.
ANDRADE, Jenne. B3 bate recorde e movimenta R$26 bilhões por dia em 2020. eInvestidor.estadao, 2021. Disponível em: https://einvestidor.estadao.com.br/investimentos/b3-recorde-26-bilhoes-dia. Acesso em: 23-mar-2022.
BINANCE, Official documentation for the Binance APIs and streams. Disponível em: <https://github.com/binance/binance-spot-api-docs/blob/master/rest-api.md>. Acesso em: 01-Abr-2021.
BAUR, Dirk G., and Thomas Dimpfl. "Realized bitcoin volatility.", 2017. SSRN 2949754 (2017): 1-26.
ECONOMIA.IG, Conheça 5 tendências tecnológicas que impulsionam o mercado financeiro (2021). Disponível em: https://economia.ig.com.br/1bilhao/2021-10-28/conheca-5-tendencias-tecnologicas-que-impulsionam-o-mercado-financeiro.html. Acesso em: 24-mar-2022.
PAIVA, Felipe Dias; ROMA, Carolina Magda da Silva. Métodos de deep learning aplicados a candlestick como estratégia de investimento. 2014.
FAMA, Eugene F. Session Topic: Stock market price behavior session chairman: Burton G. Malkiel efficient capital markets: A review of theory and empirical work. The Journal of Finance, vol. 25, no. 2, p. 383–417, 1970.
HAJRIC, Vildana. Bitcoin Declines to Lowest Level Since December's Flash Crash. Bloomberg, 2022. Disponível em: https://www.bloomberg.com/news/articles/2022-01-05/bitcoin-declines-to-lowest-level-since-december-s-flash-crash. Acesso em: 26-mar-2022.
HOLLAND, Frank. Cryptocurrency prices fall in December, and investors blame omicron, climate change. CNBC, 2021. Disponível em: https://www.cnbc.com/2021/12/29/cryptocurrency-prices-fall-in-december-and-investors-blame-omicron-climate-change.html. Acesso em: 25-mar-2022.
HOSEINZADE, E.; HARATIZADEH, S. Cnnpred: Cnn-based stock market prediction using a diverse set of variables. Expert Systems with Applications, Elsevier, v. 129, p. 273Ű285, 2019.
JANG, Huisu; LEE, Jaewook. An empirical study on modeling and prediction of Bitcoin prices with Bayesian Neural Networks based on Blockchain information. IEEE Access, vol. 6, p. 5427–5437, 2017. https://doi.org/10.1109/ACCESS.2017.2779181.
Keras: The Python Deep Learning API. Disponível em: https://keras.io/. Acesso em 07-mar-2023.
LIANG, Qiubin, et al. "Restricted Boltzmann machine based stock market trend prediction." 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2017.
MACIEL, Leandro S.; BALLINI, Rosangela. Neural networks applied to stock market forecasting: An empirical analysis. Learning and Nonlinear Models, vol. 8, no. 1, p. 3–22, 2010. https://doi.org/10.21528/lnlm-vol8-no1-art1.
MARWALA, Lufuno Ronald. Forecasting the Stock Market Index Using Artificial Intelligence Techniques. 2014. 67–70 f. 2014. https://core.ac.uk/download/pdf/39667613.pdf.
MCNALLY, Sean; ROCHE, Jason; CATON, Simon. Predicting the price of Bitcoin using machine learning. Proceedings - 26th, PDP 2018, , p. 339–343, 2018. https://doi.org/10.1109/PDP2018.2018.00060.
MALKIEL, B.G. (2005), Reflections on the Efficient Market Hypothesis: 30 Years Later. Financial Review, 40: 1-9. https://doi.org/10.1111/j.0732-8516.2005.00090.x.
MCGOWAN, Michael J. "The rise of computerized high frequency trading: use and controversy." Duke L. & Tech. Rev. 9 (2009): 1.
PONCIANO, Jonathan. ‘Looking Ugly’: Crypto Market Crash Intensifies After $300 Billion Sell-Off—How Low Can Bitcoin Prices Go?. Forbes, 2022. Disponível em: https://www.forbes.com/sites/jonathanponciano/2022/01/10/looking-ugly-crypto-market-crash-intensifies-after-300-billion-sell-off-how-low-can-bitcoin-prices-go/?sh=9acf96aa11bd. Acesso em: 26-mar-2022.
PIOTROSKI, Joseph D. "Value investing: The use of historical financial statement information to separate winners from losers." Journal of Accounting Research (2000): 1-41.
SELVIN, Sreelekshmy; VINAYAKUMAR, R.; GOPALAKRISHNAN, E. A.; MENON, Vijay Krishna; SOMAN, K. P. Stock price prediction using LSTM, RNN and CNN-sliding window model. ICACCI 2017, vol. 2017-Jan, p. 1643–1647, 2017. https://doi.org/10.1109/ICACCI.2017.8126078.
SOARES, Rebeca. CFOs brasileiros estão mais propensos a investir em tecnologia. eInvestidor.estadao, 2021. Disponível em: https://einvestidor.estadao.com.br/investimentos/cfos-investem-em-tecnologia. Acesso em: 24-mar-2022.
SHUANG, Yao; ZHANG, Weiqiang Huang Zhan. Heterogeneous Investors. no. 3, p. 2418–2421, 2011.
WANG, Jianliang; FANG, Linshan; ZHUANG, Xiang. Study and application of stock robot kaburobo based on artificial intelligence. IJCAI , p. 260–262, 2009. https://doi.org/10.1109/JCAI.2009.47.
WAQAR, M., DAWOOD, H., GUO, P., SHAHNAWAZ, M. B., & GHAZANFAR, M. A. (2017). Prediction of Stock Market by Principal Component Analysis. 2017 13th International Conference on Computational Intelligence and Security (CIS). doi:10.1109/cis.2017.00139.
Downloads
Published
How to Cite
Issue
Section
License
Proposta de Política para Periódicos de Acesso Livre
Autores que publicam nesta revista concordam com os seguintes termos:
- Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho simultaneamente licenciado sob a Licença Creative Commons Attribution que permite o compartilhamento do trabalho com reconhecimento da autoria e publicação inicial nesta revista.
- Autores têm autorização para assumir contratos adicionais separadamente, para distribuição não-exclusiva da versão do trabalho publicada nesta revista (ex.: publicar em repositório institucional ou como capítulo de livro), com reconhecimento de autoria e publicação inicial nesta revista.
- Autores têm permissão e são estimulados a publicar e distribuir seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) a qualquer ponto antes ou durante o processo editorial, já que isso pode gerar alterações produtivas, bem como aumentar o impacto e a citação do trabalho publicado (Veja O Efeito do Acesso Livre).
