Application of recurrent neural network (RNN) in bitcoin price prediction using singular value decomposition (SVD) dimensionality reduction

Edgar M. Adina; Julyver A. Tolentino; Jiaxin Shen; Hardy D. Sierra; Geldof B. Resuello

doi:10.1117/12.3012649

19 December 2023 Application of recurrent neural network (RNN) in bitcoin price prediction using singular value decomposition (SVD) dimensionality reduction

Edgar M. Adina, Julyver A. Tolentino, Jiaxin Shen, Hardy D. Sierra, Geldof B. Resuello

Author Affiliations +

Proceedings Volume 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023); 129361P (2023) https://doi.org/10.1117/12.3012649
Event: International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 2023, Istanbul, Turkey

Abstract

Bitcoin as a digital form of stock is widely researched to forecast its short-term and long-term value. Several studies have been conducted with the aim of predicting Bitcoin prices, however, data transformation techniques for better forecast in machine learning models have yet to be tackled in details. This research aims to generate a 7-day forecast of future Bitcoin prices from time-series data, using a 21-day historical data through Recurrent Neural Network (RNN) with applied Singular Value Decomposition. The methodology covered three models including a control model in which the number of singular values for SVD differ from one another while the rest of the model parameters were held constant. The study revealed that SVD transformation can reduce memory usage by 60% to 75%. However, in terms of predictive accuracy, the results indicate that there are no significant improvements on models with applied SVD over the control model. Despite this downside, this study can be useful in understanding dimensionality reduction with SVD, at the same time can serve as a steppingstone to create better predictive models from low density inputs, and this would serve as a guide for other researchers to understand Bitcoin and its economic nature.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Edgar M. Adina, Julyver A. Tolentino, Jiaxin Shen, Hardy D. Sierra, and Geldof B. Resuello "Application of recurrent neural network (RNN) in bitcoin price prediction using singular value decomposition (SVD) dimensionality reduction", Proc. SPIE 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 129361P (19 December 2023); https://doi.org/10.1117/12.3012649

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Singular value decomposition

Data modeling

Performance modeling

Neural networks

Machine learning

Systems modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years