A Hybrid Data Decomposition and Deep Learning Approach for Solana Price Prediction Incorporating Market Factors

In this study, a hybrid data decomposition model for predicting the Solana (SOL) price is proposed, integrated by advanced signal processing and machine learning techniques. The model utilizes Variational Mode Decomposition (VMD) to decompose the Solana price series into 10 intrinsic modes, each representing different frequency components of the data. These 10 decomposed modes are then used as features, along with other relevant market factors, including Solana volume, halving index, Solana trend, and Bitcoin closing price. Then, the Bidirectional Long Short-Term Memory (BiLSTM) network is chosen to capture the complex temporal dependencies in these features and forecast future prices. To evaluate the efficacy of the approach, this study compares the hybrid models performance with a baseline LSTM model, which uses only raw historical price data. The results demonstrate that the hybrid model outperforms the benchmark model, showing higher predictive accuracy and robustness. A trading simulation for models was then conducted, and the findings indicate a significant potential for the experiment model to function as an effective trading support system, reinforcing its applicability in practical market environments. This work contributes to the field of cryptocurrency price prediction by offering a more sophisticated methodology that combines time series decomposition with deep learning techniques, providing valuable insights for traders and investors.