Revolutionizing Bitcoin price forecasts: A comparative study of advanced hybrid deep learning architectures

•Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in 5-day and 15-day Bitcoin price forecasts.•Model tested across multiple loss functions for robustness.•Suggests dataset restructuring to improve m...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Finance research letters Ročník 69; s. 106136
Hlavní autoři: He, Xiangyi, Li, Yiwei, Li, Houjian
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.11.2024
Témata:
Bitcoin price
Hybrid models
Meta-heuristic optimization algorithms
Price forecast
Bitcoin price
Meta-heuristic optimization algorithms
Hybrid models
Price forecast
ISSN:1544-6123
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in 5-day and 15-day Bitcoin price forecasts.•Model tested across multiple loss functions for robustness.•Suggests dataset restructuring to improve model performance. This paper employs a deep learning network with a comprehensive architecture to forecast Bitcoin prices, enhancing accuracy by integrating two meta-heuristic optimization algorithms, INFO and NRBO. Empirical results demonstrate that the hybrid model significantly outperforms the LSTM in both fit and predictive accuracy across in-sample and out-of-sample data. Notably, the NRBO-CNN-BiLSTM-Attention model substantially improves accuracy in 5-day and 15-day forecasts, reducing the MAPE by over 50 % compared to the LSTM model, thereby significantly enhancing overall predictive performance. The robustness of our results is supported by the MCS tests. Furthermore, strategically modifying time steps in data analysis optimizes model performance.
ISSN:1544-6123
DOI:10.1016/j.frl.2024.106136