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

Badar, Wajeeha; Ramzan, Shabana; Raza, Ali; Fitriyani, Norma Latif; Syafrudin, Muhammad; Lee, Seung Won

doi:10.3390/math13121908

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

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

by

Wajeeha Badar

^1,†,

Shabana Ramzan

¹

,

Ali Raza

^2,†

,

Norma Latif Fitriyani

^3,†

,

Muhammad Syafrudin

^3,*

and

Seung Won Lee

^2,4,5,6,*

¹

Department of Computer Science & IT, The Govt. Sadiq College Women University, Bahawalpur 63100, Pakistan

²

Department of Precision Medicine, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea

³

Department of Artificial Intelligence and Data Science, Sejong University, Seoul 05006, Republic of Korea

⁴

Department of Metabiohealth, Sungkyunkwan University, Suwon 16419, Republic of Korea

⁵

Personalized Cancer Immunotherapy Research Center, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea

⁶

Department of Artificial Intelligence, Sungkyunkwan University, Suwon 16419, Republic of Korea

^*

Authors to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Mathematics 2025, 13(12), 1908; https://doi.org/10.3390/math13121908 (registering DOI)

Submission received: 6 May 2025 / Revised: 30 May 2025 / Accepted: 4 June 2025 / Published: 7 June 2025

(This article belongs to the Special Issue Machine Learning and Finance)

Download Versions Notes

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 (R²) 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

Share and Cite

MDPI and ACS Style

Badar, W.; Ramzan, S.; Raza, A.; Fitriyani, N.L.; Syafrudin, M.; Lee, S.W. Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model. Mathematics 2025, 13, 1908. https://doi.org/10.3390/math13121908

AMA Style

Badar W, Ramzan S, Raza A, Fitriyani NL, Syafrudin M, Lee SW. Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model. Mathematics. 2025; 13(12):1908. https://doi.org/10.3390/math13121908

Chicago/Turabian Style

Badar, Wajeeha, Shabana Ramzan, Ali Raza, Norma Latif Fitriyani, Muhammad Syafrudin, and Seung Won Lee. 2025. "Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model" Mathematics 13, no. 12: 1908. https://doi.org/10.3390/math13121908

APA Style

Badar, W., Ramzan, S., Raza, A., Fitriyani, N. L., Syafrudin, M., & Lee, S. W. (2025). Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model. Mathematics, 13(12), 1908. https://doi.org/10.3390/math13121908

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

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

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI