The best choice between gold and bitcoin

Tan  Fang; Yaowen  Hu

doi:10.54691/bcpbm.v22i.1232

Authors

Tan Fang
Yaowen Hu

DOI:

https://doi.org/10.54691/bcpbm.v22i.1232

Keywords:

Autoregressive Integrated Moving Average model (ARIMA), risk assessment, Dynamic Programming(DP), Analytic Hierarchy Process (AHP), Long Short-Term Memory (LSTM).

Abstract

In this paper, we use Analytic Hierarchy Process (AHP) to determine the appropriate weights and establish a bull market and bear market judgment indicator and investment risk models. Secondly, the Autoregressive Integrated Moving Average model (ARIMA) is constructed to make the expected trend for the next five years, and the optimal asset portfolio of gold assets and bitcoin assets is constructed through quadratic programming, and the Dynamic Programming (DP) model is used to compare strategies between two trades. Finally, the rationality of the model calculation is verified by the test of Long-Short-Term Memory (LSTM).

Downloads

Download data is not yet available.

References

M. T. Wang, Research on futures price trend prediction and quantitative trading strategy based on machine learning, Nanjing University of Finance and Economics,2021.

S. L. Ho, M. Xie, T.N. Goh, A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction. Computer Industry Engineer,2002; 42(2–4): 371–375.

C.A. Mitrea, C. Lee, Z. Wu, A comparison between neural networks and traditional forecasting methods: a case study. International J Engineer Bus Manage 2009; 1: 11.

Q. Liu, H. Wang, Research on the forecast and development of China’s public fiscal revenue based on ARIMA model. Theory Economics Letter 2015; 5: 482–493.

G. Box, G. Jenkins, Time series analysis, forecasting and control. San Francisco: Holden-Day, 1970.