A Comparative Analysis of Bitcoin Price Forecasting Approaches Using Machine Learning Techniques

Boyin Deng

2024

Abstract

One way to pay for products and services online is with cryptocurrency. Price swings in the cryptocurrency market may have macroeconomic repercussions because they are a component of the global economic system. Since Bitcoin is the most recognizable cryptocurrency, predicting its price has gained much attention in the current financial community. This article compares the impacts of three models — linear regression (LR), support vector machines (SVM), and long short-term memory (LSTM) — and uses stacked models to conduct additional research on the price of Bitcoin using machine learning techniques. The experimental results indicate that the LSTM model effectively captures Bitcoin price volatility, resulting in more accurate predictions. At the same time, the LR and SVM models are more straightforward in predicting the price. The stacked model captures the market trend more comprehensively and provides a more valuable reference for investors. By effectively predicting the price of Bitcoin, this study not only demonstrates the potential of different machine learning models to be applied in the financial field but also provides investors and researchers with new perspectives to help them better understand and cope with the complexity and uncertainty of the cryptocurrency market.

Paper Citation

in Harvard Style

Deng B. (2024). A Comparative Analysis of Bitcoin Price Forecasting Approaches Using Machine Learning Techniques. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 263-268. DOI: 10.5220/0013214500004568

in Bibtex Style

@conference{ecai24,
author={Boyin Deng},
title={A Comparative Analysis of Bitcoin Price Forecasting Approaches Using Machine Learning Techniques},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={263-268},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013214500004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - A Comparative Analysis of Bitcoin Price Forecasting Approaches Using Machine Learning Techniques
SN - 978-989-758-726-9
AU - Deng B.
PY - 2024
SP - 263
EP - 268
DO - 10.5220/0013214500004568
PB - SciTePress