What question did this study set out to answer?

Investigate the effectiveness of various deep learning architectures for predicting prices in cryptocurrency markets.

June 30, 20260 citationsOpen Access

An Investigation of The Contribution of Attention-Based Hybrid Deep Learning Models to Prediction Errors in Cryptocurrency Markets

AİAynur İNCEKIRIK MYMohammad Luqman YOUSUFİ NANihat Altuntepe

Key Points

Investigate the effectiveness of various deep learning architectures for predicting prices in cryptocurrency markets.
Compared multiple deep learning models including LSTM, GRU, CNN, Attention-LSTM, and Attention-GRU.
Analyzed price data for Ethereum, Solana, and BNB covering April 10, 2020, to February 12, 2026.
Evaluated model performance using metrics such as MAE, MSE, and R² after hyperparameter optimization.
GRU-based models yielded lower error values and more stable performance.
Hybrid CNN-GRU architecture showed competitive results, but attention-integrated models typically increased error values.
Findings indicate complex models do not ensure better prediction accuracy in volatile data environments.

Abstract

This study comparatively analyzes deep learning architectures for predicting the daily closing prices of Ethereum, Solana, and BNB cryptocurrencies. Given the high volatility, non-linear price movements, and noise-intensive data structures of cryptocurrency markets, accurate price modeling holds significant importance for both academic research and investment decisions. The models examined include LSTM, GRU, CNN, CNN-LSTM, CNN-GRU, Attention-LSTM, and Attention-GRU. The dataset covers the period from April 10, 2020, to February 12, 2026, at daily frequency, split into 70% training and 30% testing. Hyperparameter optimization was conducted across varying window lengths, epochs, batch sizes, neuron counts, and dropout rates. Model performance was evaluated using MAE, MSE, MAPE, and R² metrics. Results indicate that GRU-based models consistently yield lower error values and more stable performance on cryptocurrency time series. The hybrid CNN-GRU architecture produces competitive results on certain series; however, attention mechanism-integrated models generally increase error values. These findings suggest that model complexity does not guarantee superior prediction accuracy in financial time series, and that compact architectures may offer stronger generalization in highly volatile data environments. The study also addresses a methodological gap by benchmarking multiple deep learning models under identical datasets and experimental conditions.

Ask AI

Helpful

Bookmark

View Full Paper