Manuscript received December 26, 2023; revised March 4, 2024; accepted March 17, 2024; published September 26, 2024
Abstract—This study explores the application of Long Short-Term Memory (LSTM) networks to predict the price of Bitcoin over various time periods. The performance of the model is evaluated using cross-validation methods and parameter selection techniques. The results show that the LSTM model is able to accurately predict the price of Bitcoin, with performance improving as the time period of the data increases. This suggests that LSTM networks are well-suited for modeling time series. Our research study contributes to the determination of the optimal parameters and cross-validation methods for LSTM models applied to financial market data.
Keywords—bitcoin forecasting, long short-term memory, LSTM, deep learning, machine learning.
Cite: Pongsakorn Teerarassamee, Ratiporn Chanklan, Kittisak Kerdprasop, and Nittaya Kerdprasop, "The Effect of Long Short-Term Memory Forecasting with Varied Time Frames," International Journal of Machine Learning vol. 14, no. 3, pp. 107-112, 2024.
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).