Bitcoin Price Prediction Based on Machine Learning and Granger Causality Test
- DOI
- 10.2991/978-94-6463-036-7_51How to use a DOI?
- Keywords
- Bitcoin prediction; Granger Test; ARMA; MSE
- Abstract
Recently, more and more investors have seen the huge profits that the digital currency market can bring, and Bitcoin price predictions are becoming more valuable both academically and in terms of business value. In this paper, we use the daily price of bitcoin from September 12, 2016, to September 10, 2021. Data pre-processing includes moving average (MA) and BIAS. To find out the causality relationship between two factors, we use Granger causality test. Then we predict bitcoin price with Support Vector Machine (SVM) based on sliding window from machine learning methods and Autoregressive Integrated Moving Average (ARMA) method from statistical methods. The results show that there is causality relationship between gold and bitcoin. Besides, by comparing the Mean Squared errors (MSE) of 7-day-model, 14-day-model and ARMA model, we find that the ARMA model outperform the others, which reminds the investors to focus more on this model.
- Copyright
- © 2022 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Mengyu Hao AU - Feiyang Su AU - Kaifei Wang AU - Xiaoqi Zheng PY - 2022 DA - 2022/12/31 TI - Bitcoin Price Prediction Based on Machine Learning and Granger Causality Test BT - Proceedings of the 2022 2nd International Conference on Economic Development and Business Culture (ICEDBC 2022) PB - Atlantis Press SP - 342 EP - 348 SN - 2352-5428 UR - https://doi.org/10.2991/978-94-6463-036-7_51 DO - 10.2991/978-94-6463-036-7_51 ID - Hao2022 ER -