Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques

Mahir Iqbal; Muhammad Iqbal; Fawwad Jaskani; Khurum Iqbal; Ali Hassan

Research Article

Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques

Download50 downloads

Cite: BibTeX Plain Text

@ARTICLE{10.4108/eai.7-7-2021.170286,
    author={Mahir Iqbal and Muhammad Shuaib Iqbal and Fawwad Hassan Jaskani and Khurum Iqbal and Ali Hassan},
    title={Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques},
    journal={EAI Endorsed Transactions on Creative Technologies: Online First},
    volume={},
    number={},
    publisher={EAI},
    journal_a={CT},
    year={2021},
    month={7},
    keywords={data mining, visualization, machine learning, Emerging Nature Inspired Computing},
    doi={10.4108/eai.7-7-2021.170286}
}

Mahir Iqbal
Muhammad Shuaib Iqbal
Fawwad Hassan Jaskani
Khurum Iqbal
Ali Hassan
Year: 2021
Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques
CT
EAI
DOI: 10.4108/eai.7-7-2021.170286

Mahir Iqbal¹, Muhammad Shuaib Iqbal², Fawwad Hassan Jaskani¹^,*, Khurum Iqbal², Ali Hassan²

1: Department of Computer Systems Engineering, Faculty of Engineering, Islamia University of Bahawalpur
2: Department of Computer Systems Engineering, College of Electrical and Mechanical Engineering, National University of Science and Technology, Rawalpindi

*Contact email: favadhassanjaskani@gmail.com

Abstract

In the market of cryptocurrency the Bitcoins are the first currency which has gain the significant importance. To predict the market price and stability of Bitcoin in Crypto-market, a machine learning based time series analysis has been applied. Time-series analysis can predict the future ups and downs in the price of Bitcoin. For this purpose we have used ARIMA, FBProphet, XG Boosting for time series analysis as a machine learning techniques. The parameters on the basis of which we have evaluated these models are Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R2. We conduct experiments on these three techniques but after conducting time series analysis, ARIMA considered as the best model for forecasting Bitcoin price in the crypto-market with RMSE score of 322.4 and MAE score of 227.3. Additionally, this research can be helpful for investors of crypto-market.

Keywords: data mining, visualization, machine learning, Emerging Nature Inspired Computing

Received: 2021-06-27
Accepted: 2021-07-06
Published: 2021-07-07
Publisher: EAI

: http://dx.doi.org/10.4108/eai.7-7-2021.170286

Copyright © 2021 Mahir Iqbal et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.