CP-BiLSTM: Coua Porteles-Based Bidirectional Long ShortTerm Memory Networking for Cryptocurrency Price Prediction

View at publisher Summarise with VIRAT
Authors: Mahbub Arab Majumder
Cited by: 0
References: 17

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Cryptocurrency resembles the eminent key elements in the progress of financial and economic domains, which enables safe and secure money transactions. However, these currencies are not preferred as an investment prospect because of the price volatility and the unpredictable market price. However, the existing techniques fail to learn the uncertainty and fluctuations in their prices limiting their applicability for real-time price prediction. Consequently, this research proposes the Coua Porteles-Bidirectional Long Short-Term Memory (CP-BiLSTM) model for accurate prediction of cryptocurrency price from the historical price data. The proposed CP-BiLSTM model effectively captures the intricate patterns hidden in the multivariate time-series data and facilitates precise cryptocurrency price prediction. Specifically, the Coua Proteles algorithm fine-tunes the hyperparameters of the classifier and aids in improving the CP-BiLSTM model’s performance. Ultimately, the Coua Porteles optimization helps to reduce the error function and enhance the efficiency of the classifier in predicting the cryptocurrency price. The experimental results demonstrate that the proposed CP-BiLSTM approach achieves superior results attaining the MAE, MSE, RMSE, and R2-score of 2.49, 2.41, 1.55, and 0.70 respectively outperforming the other existing techniques in cryptocurrency price prediction.

Fields of Study & Subjects

Stock Market Forecasting Methods Blockchain Technology Applications and Security Time Series Analysis and Forecasting

Publication details

Journal / source
International Journal of Uncertainty Fuzziness and Knowledge-Based Systems
Volume
34
Issue
03
Pages
307–333
Publication date
1 May 2026
Language
EN