Prediction of Bitcoin Price Based on the Hidden Markov Model

DOI

10.2991/assehr.k.211209.481How to use a DOI?

Keywords

Digital currency; The Hidden Markov Model; Bitcoin price; Short-term forecast

Abstract

The prediction of the financial market has gradually attracted attention from investors. As an emerging market, digital currency has become an indispensable and essential part. The common analysis methods are mainly machine learning and its derivatives. The daily frequency data of Bitcoin prices are obtained in this paper from June 2018 to September 2020. The Hidden Markov Model (HMM) is used to predict Bitcoin prices. In the model, the input observation sequence of the model is selected, including closing price, trading volume, and hidden state. They are in line with the current mainstream market perception: bull market, stable, and bear market. The results show that the relative error of the short-term forecast is relatively low, 0.347%. Compared with traditional models and machine learning methods, the Hidden Markov Model can better identify the state of the digital currency market and predict the direction of price movements, which verifies its application feasibility in the financial market.

Copyright

© 2021 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Muxi Li
PY  - 2021
DA  - 2021/12/15
TI  - Prediction of Bitcoin Price Based on the Hidden Markov Model
BT  - Proceedings of the 2021 3rd International Conference on Economic Management and Cultural Industry (ICEMCI 2021)
PB  - Atlantis Press
SP  - 2962
EP  - 2967
SN  - 2352-5428
UR  - https://doi.org/10.2991/assehr.k.211209.481
DO  - 10.2991/assehr.k.211209.481
ID  - Li2021
ER  -