Predictive Analytics of Bitcoin Cryptocurrency Price Prediction: A Recurrent Neural Network Approach

Bitcoin is currently the most well-known cryptocurrency, and its market is extremely volatile. The evolution of the financial system is influenced by the growing popularity and commercial acceptance of investors worldwide. Investments are at risk due to the largely unknown dynamic characteristics and predictability of cryptocurrencies. Deep learning and predictive analytics are currently used in artificial intelligence approaches to analyze financial data. The aim of this study is to estimate the cryptographic value of the Bitcoin currency using the Gated Recurrent Unit model (GRU) and the Bidirectional Long-Term Memory (Bi-LSTM) model. Data collected from Yahoo Finance from July 2014 to July 2023. In addition, the performance of recurrent neural network classifiers was compared. The results show that GRU outperforms Bi-LSTM in terms of performance criteria; In other words, using the GRU model is one of the most effective methods for predicting cryptocurrency prices.