Review of deep learning models for crypto price prediction: implementation and evaluation

TL;DR

This paper addresses the challenge of forecasting cryptocurrency prices under high volatility by systematically evaluating deep learning models across univariate and multivariate inputs. The authors compare LSTM variants, CNNs, Conv-LSTM, and Transformer architectures, trained with the Adam optimizer, on four cryptocurrencies (BTC, ETH, DOGE, LTC) with supplementary Gold price data, under pre-COVID and COVID-era conditions. Key findings show that Conv-LSTM with a multivariate setup (including highly correlated crypto signals and Gold) delivers the strongest predictive accuracy in both experimental regimes, while multivariate models generally outperform univariate ones; Transformer methods underperform with limited data. The work highlights practical implications for finance practitioners and sets the stage for future work in uncertainty quantification, causal multivariate signals, and multimodal data integration.

Abstract

There has been much interest in accurate cryptocurrency price forecast models by investors and researchers. Deep Learning models are prominent machine learning techniques that have transformed various fields and have shown potential for finance and economics. Although various deep learning models have been explored for cryptocurrency price forecasting, it is not clear which models are suitable due to high market volatility. In this study, we review the literature about deep learning for cryptocurrency price forecasting and evaluate novel deep learning models for cryptocurrency stock price prediction. Our deep learning models include variants of long short-term memory (LSTM) recurrent neural networks, variants of convolutional neural networks (CNNs), and the Transformer model. We evaluate univariate and multivariate approaches for multi-step ahead predicting of cryptocurrencies close-price. We also carry out volatility analysis on the four cryptocurrencies which reveals significant fluctuations in their prices throughout the COVID-19 pandemic. Additionally, we investigate the prediction accuracy of two scenarios identified by different training sets for the models. First, we use the pre-COVID-19 datasets to model cryptocurrency close-price forecasting during the early period of COVID-19. Secondly, we utilise data from the COVID-19 period to predict prices for 2023 to 2024. Our results show that the convolutional LSTM with a multivariate approach provides the best prediction accuracy in two major experimental settings. Our results also indicate that the multivariate deep learning models exhibit better performance in forecasting four different cryptocurrencies when compared to the univariate models.

Figures (23)

• Figure 1: Architecture of a multilayer perceptron showing the input, hidden and output layers and interconnections between them, also the parameters in each layer(weight, bias and input).
• Figure 2: Architecture of Elman RNN that consists of input, hidden, context (state), and output layers
• Figure 3: LSTM network showing the input, hidden (LSTM cell), and output layers. LSTM cell extract information from input feature $x$ in over all time span.
• Figure 4: BD-LSTM Network showing the input, output and backward&forward layer with the connection between them. These two hidden layer combine forward and backward information flow to enhance the ability of model to acquire information.
• Figure 5: Encoder-Decoder LSTM Network showing encoder and decoder transfer sequence with encoder vector.