Hybrid CNN–Transformer Model for Time-Series Prediction

Time-series prediction plays a vital role in numerous real-world applications such as energy forecasting, financial analysis, healthcare monitoring, and industrial automation. Traditional statistical and deep learning models often face limitations in capturing both short-term local patterns and long-term temporal dependencies. To address this challenge, this paper proposes a Hybrid CNN–Transformer model for accurate time-series forecasting. The Convolutional Neural Network (CNN) component extracts local temporal features, while the Transformer encoder captures long-range dependencies using self-attention mechanisms. Experimental evaluation on benchmark datasets demonstrates that the proposed hybrid model outperforms conventional CNN, LSTM, and standalone Transformer models in terms of prediction accuracy and robustness. The results confirm the effectiveness of combining CNN and Transformer architectures for time-series prediction tasks.