Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model

Wajeeha Badar, Shabana Ramzan, Ali Raza, Norma Latif Fitriyani, Muhammad Syafrudin () and Seung Won Lee ()
Additional contact information
Wajeeha Badar: Department of Computer Science & IT, The Govt. Sadiq College Women University, Bahawalpur 63100, Pakistan
Shabana Ramzan: Department of Computer Science & IT, The Govt. Sadiq College Women University, Bahawalpur 63100, Pakistan
Ali Raza: Department of Precision Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea
Norma Latif Fitriyani: Department of Artificial Intelligence and Data Science, Sejong University, Seoul 05006, Republic of Korea
Muhammad Syafrudin: Department of Artificial Intelligence and Data Science, Sejong University, Seoul 05006, Republic of Korea
Seung Won Lee: Department of Precision Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea

Mathematics, 2025, vol. 13, issue 12, 1-22

Abstract: Predicting the price of Bitcoin is crucial, primarily because of the market’s rapid volatility and non-linear environment. For enhanced prediction of the price of Bitcoin, this research proposed a novel interpretable hybrid technique that combines long short-term memory (LSTM) networks with convolutional neural networks (CNN). Deep variational autoencoders (VAE) are used in the stage of preprocessing to determine noticeable patterns in datasets by learning features from historical Bitcoin price data. The CNN-LSTM model additionally implies Shapley additive explanations (SHAP) to promote interpretability and clarify the role of various features. For better performance, the methodology used data cleaning, preprocessing, and effective machine-learning techniques. The hybrid CNN + LSTM model, in collaboration with VAE, obtains a mean squared Error (MSE) of 0.0002, a mean absolute error (MAE) of 0.008, and an R-squared (R 2 ) of 0.99, based on the experimental results. These results show that the proposed model is a good financial forecast method since it effectively reflects the complex dynamics of primary changes in the price of Bitcoin. The combination of deep learning and explainable artificial intelligence improves predictive accuracy as well as transparency, thus qualifying the model as highly useful for investors and analysts.

Keywords: bitcoin price prediction; hybrid model; CNN; LSTM; variational autoencoders; SHAP; time-series forecasting (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/12/1908/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/12/1908/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:12:p:1908-:d:1674071

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().