Gold and Bitcoin Price Prediction Model Based on Grey Model
DOI:
https://doi.org/10.54097/hbem.v20i.14745Keywords:
RNN, HMM, Prediction Model, Grey Model.Abstract
As a traditional equivalent, gold has long been a symbol of wealth, traded by countless people. However, with the progress of science and technology, virtual currency has gradually entered our vision and has a great impact on people's life. The purpose of this paper is to accurately predict the price of gold and bitcoin on the premise that the initial conversion is only $1,000, and ultimately maximize the asset. Therefore, the grey model is established to make the prediction. Its advantage is that it improves the long-term dependence problem in RNN; GM generally outperforms temporal recurrent neural networks (RNN) and Hidden Markov models (HMM). By calculation, the price of gold in 2016 was $1,325 and the price of bitcoin was $622; Five years from now, the forecast price for gold is $1,788 and the forecast price for bitcoin is $46,192, with an average margin of error of just 1.7%. According to the model built in this article, investors can predict the next three days based on today's data, so that they can adjust our portfolios based on the forecast results.
Downloads
References
Putro W A P, Prasetyo P W A, Gagas M P. Designing the Quick Cash Payment System prototype by using cash withdrawal services through minimarket as an alternative solution for secure money transfer from bank customers to non-bank customers [J]. IOP Conference Series: Materials Science and Engineering, 2020, 852 (1).
Xinchen Z, Linghao Z, Qincheng Z, et al. A Novel Bitcoin and Gold Prices Prediction Method Using an LSTM-P Neural Network Model [J]. Computational Intelligence and Neuroscience, 2022, 2022.
Yang Y, Xiong J, Zhao L, et al. A Novel Method of Blockchain Cryptocurrency Price Prediction Using Fractional Grey Model [J]. Fractal and Fractional, 2023, 7 (7).
Lan W, Nan L, Ming X. An Ensemble Learning Method for the Kernel-Based Nonlinear Multivariate Grey Model and its Application in Forecasting Greenhouse Gas Emissions [J]. Journal of Mathematics, 2022, 2022.
Yao T, Wang Z. Crude oil price prediction based on LSTM network and GM (1, 1) model [J]. Grey Systems Theory and Application, 2020, ahead-of-print(ahead-of-print).
Rathnayaka T K R, Seneviratna D. Taylor series approximation and unbiased GM (1, 1) based hybrid statistical approach for forecasting daily gold price demands [J]. Grey Systems: Theory and Application, 2019, 9 (1).
Kundu, Debasis. Stationary GE-Process and its Application in Analyzing Gold Price Data [J]. Sankhya B, 2021, 84 (2).
H. A A, H. H T A. Bitcoin Price Forecasting and Trading: Data Analytics Approaches [J]. Electronics, 2022, 11 (24).
Jin Fei. Optimization research and application of GM (1, 1), a dynamic model of grey system theory [D]. Yanshan University, 2012.
Xiao Li-Fang, Wang Hao, Duan Mei. Optimal combination method of grey model GM (1, 1) based on posterior difference test [J]. Mathematics in Practice and Understanding, 2019, 51 (12): 1-10.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
