2025
Comparison of neural network models for prediction cryptocurrency price volatility in trading pairs
A comparative evaluation of five state-of-the-art machine learning models, such as Temporal Fusion Transformer (TFT), Temporal Convolutional Network (TCN), XGBoost, Random Forest, and a CNN-LSTM hybrid, for forecasting cryptocurrency price volatility across major trading pairs shows that TFT achieves the lowest test loss and highest classification accuracy, outperforming other architectures.
S. Mukhanov, Kaisar Bekbolat, I. Bazarbekov et al.
· AI@DTESI · 0 citations