The comprehensive experimental analysis in this work shows that the universal model trained on a time series from the same class reliably outperforms the other models and is better than those reported for other universal approaches in the literature.
Abstract
The cryptocurrency evolution series has piqued the interest of many researchers seeking to understand the underlying factors that drive evolution and predict future values, yielding useful insights across social and economic fields. The paper introduces a new methodology implementing a cluster-based universal framework to forecast daily cryptocurrency realized volatility from exogenous inputs. The mathematical models include internal and external determinants, and, in the proposed universal model, the input set is further augmented with time-series data on realized cryptocurrency volatility based on the hierarchical Dynamic Time Warping (DTW) clustering dendrogram. The forecasting stage is performed by the regressors in the Deep Learning (DL) class. The performance of the models is assessed using Mean Accuracy Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Mean Directional Accuracy (MDA). The final stage of the proposed methodology is the model interpretation carried out by the Gradient Explainer technique. The comprehensive experimental analysis in our work shows that the universal model trained on a time series from the same class reliably outperforms the other models. In addition, the results obtained are better than those reported for other universal approaches in the literature.
Cryptocurrency markets are highly volatile, nonlinear, and affected by several internal and external market factors, making price forecasting a challenging task. Accurate cryptocurrency price forecasting can support investors, traders, and financial analysts in making informed decisions. This research paper presents a comparative analysis of machine learning and deep learning models for cryptocurrency price forecasting using historical Aave (AAVE) cryptocurrency data. The dataset consists of 275 records and 10 features, including Date, High, Low, Open, Close, Volume, and Marketcap. The Close price is selected as the target variable, while High, Low, Open, Volume, and Marketcap are used as predictor variables. Five models are implemented and compared: Linear Regression, Support Vector Regression, Random Forest Regressor, XGBoost Regressor, and Long Short-Term Memory. The models are evaluated using Mean Absolute Error, Root Mean Square Error, Mean Absolute Percentage Error, R-squared score, and directional accuracy. Experimental results show that the LSTM model achieved the best performance with the lowest RMSE of 2.74, MAE of 1.78, MAPE of 3.91%, and R-squared score of 0.965. The results indicate that deep learning models, especially LSTM, are more suitable for capturing temporal dependencies and nonlinear patterns in cryptocurrency price data.
Rukhsar Zaka, Faiza Irfan, Sidra Rehman et al.· International Journal of Adv...· 0 citations
Accurate prediction of Bitcoin market prices is challenging because of extreme volatility, nonlinear dynamics and rapid sentiment-driven fluctuations observed in the cryptocurrency market, especially Bitcoin. In this research, the authors investigate the use of machine learning and deep learning methods for forecasting Bitcoin prices using historical market data, technical indicators, and sentiment analysis from social media. A comprehensive dataset was used to develop and test three experimental setups from 2015 to 2024. The first configuration, an LSTM model was trained on historical OHLCV (Open, High, Low, Close, Volume) data only. In the second setup, the model was improved with the inclusion of technical indicators based on market behavior, including momentum indicators and trend indicators. The third configuration used social media sentiment features (extracted from over 2.5 million tweets related to Bitcoin, employing polarity and subjectivity scoring via TextBlob), added to the previous configuration. The results show that the LSTM model with technical indicators gave the best prediction performance with R2 of 0.9084 and Mean Absolute Error (MAE) of 0.0387, which is 8.5% better than the historical data-only model. By comparison, the accuracy of prediction did not significantly improve with the addition of Twitter sentiment features. The feature importance analysis also revealed that Relative Strength Index (RSI) and MACD histogram were the most significant features in predicting the price movements of Bitcoin. The study brings three significant findings: (1) a methodological framework based on LSTM neural networks for comparing the performance of various sets of features in predicting Bitcoin prices; (2) the discovery of the most relevant features in cryptocurrency markets; and (3) proof that technical indicators have a significant impact on the predictive accuracy of this model, while social media sentiment has a minor impact under the circumstances. The results offer valuable implications for researchers and practitioners building data-driven models for predicting cryptocurrencies.
Sedeeq Hasan Banna, Ammar Ahmed Othman, Khaled Al-Raddah· SISTEMASI· 0 citations
This work attempts to provide a thorough comparative analysis mapping the precise accuracy–efficiency trade-off between Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models under a standardized Grid Search hyperparameter optimization pipeline using a recent Bitcoin closing-price dataset.
This study investigates short-term predictive relationships between major cryptocurrencies—specifically Ethereum (ETH) and Solana (SOL)—and their respective sub-tokens (DYDX, UNI, GRT, JUP, RAY, PYTH) by employing a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. Using high-frequency data across different time intervals (15 minutes, 1 hour, and 4 hours), the study examines whether price movements in major tokens are associated with enhanced short- and medium-term predictability of ecosystem-based sub-tokens. The empirical results indicate that the hybrid CNN-LSTM model achieves strong forecasting performance at shorter time horizons, while prediction accuracy declines as the time interval increases, reflecting the limiting role of market volatility. The results indicate statistically significant short-term predictive relationships and pronounced co-movement patterns between major token movements and sub-token pricing behavior, particularly at higher-frequency intervals, suggesting that Ethereum and Solana provide informative signals related to ecosystem-wide liquidity and trading activity.
Mehmet Çınar, Muhammed Apak· Afyon kocatepe üniversitesi...· 0 citations
Cryptocurrency markets are non-stationary, making price forecasting inherently unreliable over time. This study examines whether the choice of target variable has more impact on forecast stability than the choice of model architecture. Five models are evaluated across two target formulations: raw Bitcoin price and 1-hour percentage change. The models tested are Naive Forecast, AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Bidirectional LSTM, and Gated Recurrent Unit (GRU), each trained and assessed over a 27-day test window using live data collected at 5-minute intervals across a rolling six-week period. Drift detection using the Wasserstein distance confirmed that raw price exhibits significantly greater distributional shift than percentage change over the same timeframe. Models trained on raw price produced directional accuracy below 50% across all learned architectures, with visible degradation over the test window. The Naive Forecast outperformed all learned models on both RMSE ($110.34) and MAE ($66.08). Models trained on percentage change maintained substantially higher accuracy: LSTM achieved 74.7% directional accuracy, while BiLSTM and GRU both reached 72.8%, with no comparable decay observed. The results indicate that model decay in Bitcoin forecasting is driven primarily by data drift in the target variable rather than by limitations in the predicting architecture. When the target is stationary, all models tested retain their accuracy across the full evaluation window.
