Utilizando HMM para previsão de preço e estratégia de investimento em criptomoedas BitCoin
Resumo
O aprendizado de máquina está cada vez mais presente no dia a dia da população. Essas técnicas podem auxiliar, por exemplo, na tomada de decisão sobre investimentos no mercado de ações a fim de reduzir os riscos associados às operações financeiras. Novos agentes estão cada vez mais presentes na sociedade, sendo o Bitcoin um exemplo claro da inserção tecnológica nas transações financeiras. Entretanto, como toda moeda, é possível negociar no mercado de ações, apostando em sua valorização. Neste artigo, três técnicas de modelagem matemática são utilizadas a fim de prever o valor futuro do Bitcoin. Dentre todas as técnicas analisadas o Modelo Oculto de Markov (HMM) obteve a melhor performance e um retorno de investimento de mais de 50.000 U$.
Referências
Ariyo, A. A., Adewumi, A. O., and Ayo, C. K. (2014). Stock price prediction using the arima model. In 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, pages 106–112. IEEE.
Baum, L. E. and Petrie, T. (1966). Statistical inference for probabilistic functions of finite state markov chains. The annals of mathematical statistics, 37(6):1554–1563.
Chappell, D. R. et al. (2019). Regime heteroskedasticity in bitcoin: A comparison of markov switching models. Journal of Applied Economic Sciences (JAES), 14(65):621–641.
de Souza e Silva, E. G., Legey, L. F., and de Souza e Silva, E. A. (2010). Forecasting oil price trends using wavelets and hidden markov models. Energy Economics, 32(6):1507–1519.
Ghosh, A. K., Ullah, A. S., and Kubo, A. (2019). Hidden markov model-based digital twin construction for futuristic manufacturing systems. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 33(3):317–331.
Gupta, A. and Dhingra, B. (2012a). Stock market prediction using hidden markov models. In 2012 Students Conference on Engineering and Systems, pages 1–4. IEEE.
Gupta, A. and Dhingra, B. (2012b). Stock market prediction using hidden markov models. StockStock, pages 1–4.
Hua, Y. (2020). Bitcoin price prediction using arima and lstm. In E3S Web of Conferences, volume 218. EDP Sciences.
Jesus, E., Chicarino, V., Albuquerque, C., and Rocha, A. (2018a). A survey of how to use blockchain to secure internet of things and the stalker attack. Security and Communication Networks, 2018:1–27.
Jesus, E. F., Chicarino, V. R. L., Albuquerque, C., and de A. Rocha, A. A. (2018b). In Anais do Stalker uma nova estratégia para o atacante egoísta em blockchains. XXXVI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Porto Alegre, RS, Brasil. SBC.
Koki, C., Leonardos, S., and Piliouras, G. (2019). Do cryptocurrency prices camouage In Multidisciplinary latent economic effects? a bayesian hidden markov approach. Digital Publishing Institute Proceedings, volume 28, page 5.
Koki, C., Leonardos, S., and Piliouras, G. (2020). Exploring the predictability of cryptocurrencies via bayesian hidden markov models. arXiv preprint arXiv:2011.03741.
Li, R., Arzaghi, E., Abbassi, R., Chen, D., Li, C., Li, H., and Xu, B. (2020). Dynamic maintenance planning of a hydro-turbine in operational life cycle. Reliability Engineering System Safety, 204:107129.
Maupin, T. (2019). Can bitcoin, and other cryptocurrencies, be modeled effectively with a markov-switching approach? Nakamoto, S. and Bitcoin, A. (2008). A peer-to-peer electronic cash system. Bitcoin.– URL: https://bitcoin.org/bitcoin.pdf, 4.
Nguyen, N. (2017). An analysis and implementation of the hidden markov model to technology stock prediction. Risks, 5(4):62.
Schuller, B., Rigoll, G., and Lang, M. (2003). Hidden markov model-based speech emotion recognition. In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP ’03)., volume 2, pages II–1.
Silveira, F. and de Souza e Silva, E. (2012). Predicting packet loss statistics with hidden markov models for fec control. Computer Networks, 56(2):628–641.
Van Compernolle, D. (1989). Noise adaptation in a hidden markov model speech recognition system. Computer Speech Language, 3(2):151–167.
Varga, A. P. and Moore, R. K. (1990). Hidden markov model decomposition of speech and noise. In International Conference on Acoustics, Speech, and Signal Processing, pages 845–848 vol.2.
Wu, C., Lu, C., Ma, Y., and Lu, R. (2018). A new forecasting framework for bitcoin price with lstm. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pages 168–175.
Wu, C.-H., Lu, C.-C., Ma, Y.-F., and Lu, R.-S. (2018). A new forecasting framework for bitcoin price with lstm. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pages 168–175. IEEE.
Xu, Y. (2020). Bitcoin Price Forecast Using LSTM and GRU Recurrent networks, and Hidden Markov Model. PhD thesis, UCLA.
Baum, L. E. and Petrie, T. (1966). Statistical inference for probabilistic functions of finite state markov chains. The annals of mathematical statistics, 37(6):1554–1563.
Chappell, D. R. et al. (2019). Regime heteroskedasticity in bitcoin: A comparison of markov switching models. Journal of Applied Economic Sciences (JAES), 14(65):621–641.
de Souza e Silva, E. G., Legey, L. F., and de Souza e Silva, E. A. (2010). Forecasting oil price trends using wavelets and hidden markov models. Energy Economics, 32(6):1507–1519.
Ghosh, A. K., Ullah, A. S., and Kubo, A. (2019). Hidden markov model-based digital twin construction for futuristic manufacturing systems. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 33(3):317–331.
Gupta, A. and Dhingra, B. (2012a). Stock market prediction using hidden markov models. In 2012 Students Conference on Engineering and Systems, pages 1–4. IEEE.
Gupta, A. and Dhingra, B. (2012b). Stock market prediction using hidden markov models. StockStock, pages 1–4.
Hua, Y. (2020). Bitcoin price prediction using arima and lstm. In E3S Web of Conferences, volume 218. EDP Sciences.
Jesus, E., Chicarino, V., Albuquerque, C., and Rocha, A. (2018a). A survey of how to use blockchain to secure internet of things and the stalker attack. Security and Communication Networks, 2018:1–27.
Jesus, E. F., Chicarino, V. R. L., Albuquerque, C., and de A. Rocha, A. A. (2018b). In Anais do Stalker uma nova estratégia para o atacante egoísta em blockchains. XXXVI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Porto Alegre, RS, Brasil. SBC.
Koki, C., Leonardos, S., and Piliouras, G. (2019). Do cryptocurrency prices camouage In Multidisciplinary latent economic effects? a bayesian hidden markov approach. Digital Publishing Institute Proceedings, volume 28, page 5.
Koki, C., Leonardos, S., and Piliouras, G. (2020). Exploring the predictability of cryptocurrencies via bayesian hidden markov models. arXiv preprint arXiv:2011.03741.
Li, R., Arzaghi, E., Abbassi, R., Chen, D., Li, C., Li, H., and Xu, B. (2020). Dynamic maintenance planning of a hydro-turbine in operational life cycle. Reliability Engineering System Safety, 204:107129.
Maupin, T. (2019). Can bitcoin, and other cryptocurrencies, be modeled effectively with a markov-switching approach? Nakamoto, S. and Bitcoin, A. (2008). A peer-to-peer electronic cash system. Bitcoin.– URL: https://bitcoin.org/bitcoin.pdf, 4.
Nguyen, N. (2017). An analysis and implementation of the hidden markov model to technology stock prediction. Risks, 5(4):62.
Schuller, B., Rigoll, G., and Lang, M. (2003). Hidden markov model-based speech emotion recognition. In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP ’03)., volume 2, pages II–1.
Silveira, F. and de Souza e Silva, E. (2012). Predicting packet loss statistics with hidden markov models for fec control. Computer Networks, 56(2):628–641.
Van Compernolle, D. (1989). Noise adaptation in a hidden markov model speech recognition system. Computer Speech Language, 3(2):151–167.
Varga, A. P. and Moore, R. K. (1990). Hidden markov model decomposition of speech and noise. In International Conference on Acoustics, Speech, and Signal Processing, pages 845–848 vol.2.
Wu, C., Lu, C., Ma, Y., and Lu, R. (2018). A new forecasting framework for bitcoin price with lstm. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pages 168–175.
Wu, C.-H., Lu, C.-C., Ma, Y.-F., and Lu, R.-S. (2018). A new forecasting framework for bitcoin price with lstm. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pages 168–175. IEEE.
Xu, Y. (2020). Bitcoin Price Forecast Using LSTM and GRU Recurrent networks, and Hidden Markov Model. PhD thesis, UCLA.
Publicado
16/08/2021
Como Citar
SILVA, Luiz Phillip Q.; ARAÚJO, André P. D. de; COTA, Daniel O. C.; COTA, Gabriel O. C.; ROCHA, Antonio A. de A..
Utilizando HMM para previsão de preço e estratégia de investimento em criptomoedas BitCoin. In: WORKSHOP EM BLOCKCHAIN: TEORIA, TECNOLOGIAS E APLICAÇÕES (WBLOCKCHAIN), 4. , 2021, Uberlândia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 134-147.
DOI: https://doi.org/10.5753/wblockchain.2021.17136.
