Hybrid gated recurrent unit bidirectional-long short-term memory model to improve cryptocurrency prediction accuracy

Abstract

Cryptocurrency is a digital currency used in financial systems that utilizes blockchain technology and cryptographic functions to gain transparency and decentralization. Because cryptocurrency prices fluctuate so much, tools for monitoring and forecasting them are required. Long short-term memory (LSTM) is a deep learning model that is capable of strongly predicting data time series. LSTM has been used in previous studies to predict the common currency. In this study, we used the gate recurrent unit (GRU) and bidirectional–LSTM (Bi-LSTM) hybrid model to predict cryptocurrency prices to improve the accuracy and normalize the root mean square error (RMSE) score of previously proposed prediction Using four cryptocurrencies (Bitcoin, Ethereum, Ripple, and Binance), the LSTM model predicts the Bitcoin. The RMSE obtained based on the best experimental results was 2343, Ethereum 10 epoch 203.89, Binance 200 epoch 32.61, and Ripple 200 epoch 0.077, while the mean absolute percentage error (MAPE) obtained for Bitcoin was 4.0%, Ethereum 5.31%, Binance 5.64%, and Ripple 4.83%. The results after normalization RMSE are Bitcoin 0.0062, Ethereum 0.063, Binance 0.073, and Ripple 0.055. The GRU Bi-LSTM hybrid model obtained very good results, yielding small RMSE results. After normalization, the results get closer to 0 and MAPE scores below 10% with RMSE.