Deep Learning-Based Cryptocurrency Price Prediction

Abstract

Abstract— Cryptocurrency markets have experienced rapid growth, attracting attention from investors, traders, and researchers. Accurate price prediction is critical for effective risk management and investment strategies. This paper proposes a hybrid deep learning model that combines Transformer Encoder and Gated Recurrent Unit (GRU) architectures with technical indicators to predict cryptocurrency prices. The model uses daily OHLC data and selected technical indicators, achieving strong predictive performance on BTC-USD, ETH-USD, and BNB-USD. The results demonstrate that the model accurately captures price trends with low prediction errors, achieving RMSE and MAPE values of 2607.32 and 3.70% for BTC-USD, 205.86 and 6.02% for ETH-USD, and 21.45 and 4.09% for BNB-USD, respectively. These findings highlight the model’s potential for developing adaptive trading strategies and advancing decision-making in cryptocurrency markets.