Prediction Model of Gold Yield Time Series Based on ARIMA and LSTM

Authors

  • Duo Wang

DOI:

https://doi.org/10.54691/bcpbm.v38i.4123

Keywords:

Gold returns; ARIMA; LSTM; Financial.

Abstract

To improve the accuracy of stock forecast returns, this paper will select ARIMA and LSTM forecasting models from traditional forecasting models and nonlinear forecasting models, respectively, to establish a more suitable forecasting method for gold returns. As the research object, this paper will choose the gold return from January 1, 2000 to April 30, 2020, and take May 2020 as the forecast time range. First, this paper will introduce the background of gold yield. Next, this paper will explain the definition of the ARIMA model as well as the LSTM model and the research methodology. Then, this paper will compare the models set up for forecasting gold yields under different parameters. Finally, this paper chooses the model with the most suitable parameters for the normalized values and show by the results that both models are not suitable for analyzing the gold yield. The research of this paper has important theoretical and practical significance for the prediction in the financial field.

Downloads

Download data is not yet available.

References

Barro, R. and Misra, S., Gold Returns. The Economic Journal, 2016, 126(594).1293-1317.

Malliaris, A., & Malliaris, M. What drives gold returns? A decision tree analysis. Finance Research Letters,2015, 13, 45-53.

Xu L. P.,Luo M. C.. Short-term analysis of gold price forecast based on ARIMA model. Finance and Economics Science, 2011 (01), pp.26-34.

Hochreiter, S., & Schmidhuber, J. Long short-term memory. Neural computation, 1997, 9(8), 1735–1780.

Saxena, S. LSTM | Introduction to LSTM | Long Short Term Memor. 2021.

Dolphin, R. LSTM Networks | A Detailed Explanation. 2020.

Finance.yahoo.com. https://finance.yahoo.com/, last accessed 2022/10/02.

Song H , Du D , Li Y . Research on Precise Demand Forecast of Retail Commodities Based on LSTM-ARIMA Joint Model. Journal of Physics: Conference Series, 2021, 1865(4):042049-.

Ding Yan, Xu Dehe, Cao Lianhai, etc Study on the Suitability of LSTM and ARIMA Models for Drought Prediction Based on CEEMD -- Taking Xinjiang as an Example Arid Zone Research, 2022, 39 (3): 11

Bali V, Kumar A, Gangwar S . A Novel Approach for Wind Speed Forecasting Using LSTM-ARIMA Deep Learning Models. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 2020, 11.

Downloads

Published

2023-03-02