Prediction of DASH Price Based on Machine Learning
Xinze Wu
2024
Abstract
Contemporarily, cryptocurrency attracts lots of investors on account of its high volatility. This study investigates the use of machine learning models to predict the price of DASH, a leading cryptocurrency known for its focus on privacy and speed. By applying a range of models, including Ordinary Least Squares (OLS) regression, Random Forest, and LightGBM, this paper aims to determine the most effective approach for forecasting DASH prices. The data set consists of daily DASH prices over a four-year period, from January 2020 to August 2024, with technical indicators such as the 50-day Simple Moving Average (SMA_50), MACD, and RSI_14 serving as the independent variables. The findings indicate that while OLS regression provides a basic benchmark, its predictive accuracy is limited. In contrast, the Random Forest model showed better performance, but it was the LightGBM model that delivered the highest accuracy, effectively capturing the non-linear relationships in the data While the results are encouraging, the study recognizes several limitations, such as the omission of sentiment indicators and intraday data. Future investigations could benefit from incorporating these elements to improve the accuracy of predictions. These results contribute to the growing literature on cryptocurrency price prediction, provides practical insights for investors and traders seeking to leverage machine learning in their decision-making processes in the meantime.
DownloadPaper Citation
in Harvard Style
Wu X. (2024). Prediction of DASH Price Based on Machine Learning. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 164-169. DOI: 10.5220/0013208500004568
in Bibtex Style
@conference{ecai24,
author={Xinze Wu},
title={Prediction of DASH Price Based on Machine Learning},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={164-169},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013208500004568},
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 - Prediction of DASH Price Based on Machine Learning
SN - 978-989-758-726-9
AU - Wu X.
PY - 2024
SP - 164
EP - 169
DO - 10.5220/0013208500004568
PB - SciTePress