Presenting a new deep learning-based method with the incorporation of error effects to predict certain cryptocurrencies

In recent years, with the emergence of blockchain technology, we have witnessed a remarkable increase in the use of digital currencies. However, investing in the digital currency market carries a high level of risk due to the market's erratic behavior and high price fluctuations. Consequently, the need for an appropriate model for intelligent prediction and risk management is perceived. Motivated by the above subject, we propose a novel approach based on a deep neural network with a focus on error patterns. The proposed approach is based on the theory of non-random walks and assumes that there are predictable components in the price movements of cryptocurrencies. This new approach attempts to improve prediction results by modeling residual values and incorporating their impact on the main predictions. The time scope of this research is from October 31, 2018, to December 30, 2023, on a daily basis, spanning Five years. In this study, we utilized Long Short-Term Memory (LSTM) as the main prediction model and Vector Autoregression (VAR) for forecasting noise in three well-known cryptocurrencies: Bitcoin, Ethereum, and Binance Coin (BNB). The results indicate that the proposed approach has been able to enhance the predictions.