Enhancing digital cryptocurrency trading price prediction with an attention-based convolutional and recurrent neural network approach: The case of Ethereum

• Published in: Finance research letters Vol. 67; p. 105846
• Main Authors: Shang, Dawei, Guo, Ziyu, Wang, Hui
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2024
• Subjects: Attention-based allocation function; Cryptocurrency price; Improved convolutional neural network; Interpretable machine learning approach; Times series; Attention-based allocation function; Interpretable machine learning approach; Cryptocurrency price; Times series; Improved convolutional neural network
• ISSN: 1544-6123
• DOI: 10.1016/j.frl.2024.105846

•Proposes an interpretable machine learning (IML) approach.•Improves recurrent neural network framework for cryptocurrency forecasting.•Incorporated an attention mechanism-enhanced distribution function algorithm.•Proposes attention-based approach improved interpretability and accuracy.•The new approach has higher accuracy than the GRU and ARIMA approaches. To predict Ethereum price fluctuations, this study proposes a new two-stage Machine Learning approach using an improved convolutional neural network and a recurrent neural network framework, integrating an attention mechanism-based distribution function algorithm. We construct a dataset and perform model training, fitting, and forecasting. The results indicate that compared with traditional neural networks and time-series models such as GRU and ARIMA, respectively, this approach can effectively use the data information of digital cryptocurrency and improve the prediction accuracy and interpretability of attention-based allocation functions. This study contributes to the literature by offering a new approach for stakeholders.