Short-Term Forecasting in Bitcoin Time Series Using LSTM and GRU RNNs

  • Marcelo de Caux Universidade Federal Fluminense
  • Flavia Bernardini Universidade Federal Fluminense
  • Jose Viterbo Universidade Federal Fluminense


In recent years, bitcoin has become a very attractive investment in financial industry, which is not controlled by governments, but is based on trust between transfers under the technology of block chain. Hence, forecasting future bitcoin cryptocurrency values is a problem that has attracted the attention of many researchers in the field, while proving to be a very challenging problem. This work presents an experimental analysis using LSTM and GRUs for forecasting bitcoin values in a minute-granulated time for the entire next day. To this end we also present our methodology for conducting the experiments. The final goal is to create the core of a financial prediction tool around the RNNs. In our experiments, we achieved interesting results such as a SMAPE of 0.0002, a RMSE of US$ 3.844 and a rRMSE of 0.0028 in a day where bitcoin rates vary from US$ 13.2K and US$ 14.6K, surpassing the results of SMAPE found in the literature and proposed limit of SMAPE smaller than 0.007 for forecasts.

Palavras-chave: kdmile, Bitcoin, Financial Forecasting, Recurrent Neural Network, LSTM, GRU


Chauhan, A., Kumar, M., and Saini, V. K. Bitcoin financial forecasting. Int. J. Advanced Research, Ideas and Innovations in Technology 5 (2), 2019.

Cowpertwait, P. and Metcalfe, A. Introductory Time Series with R. Springer, 2009.

Gulli, A. and S., P. Deep Learning with Keras. Packt Publishing Ltd., 2017.

Mangala, N., Bhat, A., Avabratha, G., and N.Bhat. BITCOIN price prediction using machine learning. Int. J. Information and Computing Science, 2019.

Rathan, K., Sai, S. V., and Manikanta, T. S. Crypto-currency price prediction using decision tree and regression techniques. In Proc. 3rd Int. Conf. on Trends in Electronics and Informatics (ICOEI 2019), 2019.

Sezer, O. B., Gudelek, M. U., and Ozbayoglu, A. M. Financial time series forecasting with deep learning : A systematic literature review: 2005–2019, 2020. Available at

Shcherbakov, M., Brebels, A., Shcherbakova, N., Tyukov, A., Janovsky, T., and Kamaev, V. A survey of forecast error measures. World Applied Sciences Journal vol. 24, pp. 171–176, 2013.

Uras, N., Marchesi, L., Marchesi, M., and Tonelli, R. Forecasting bitcoin closing price series using linear regression and neural networks models, 2020. Preprint submitted to Elsevier, in evaluation process. Available at

Yamak, P. T., Yujian, L., and Gadosey, P. K. A comparison between arima, lstm, and gru for time series forecasting. In Proc. 2nd International Conference on Algorithms, 2019.
DE CAUX, Marcelo; BERNARDINI, Flavia; VITERBO, Jose. Short-Term Forecasting in Bitcoin Time Series Using LSTM and GRU RNNs. In: SYMPOSIUM ON KNOWLEDGE DISCOVERY, MINING AND LEARNING (KDMILE), 8. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 97-104. ISSN 2763-8944. DOI: