Welcome to Francis Academic Press

Academic Journal of Business & Management, 2022, 4(4); doi: 10.25236/AJBM.2022.040416.

Predict the Price Change over Time with LSTM Neural Network


Zibin Bi1, Ruixuan Hao1, Ziqi Dai2

Corresponding Author:
Zibin Bi

1Shihezi University, Shihezi, Xinjiang, 832061, China

2Anhui Jianzhu University, Hefei, Anhui, 230601, China


Time series analysis can be used to analyze the price. The LSTM Neural Network model is used to predict the price. Moreover, the correlation analysis between variables and price is conducted. By improving and optimizing the mathematical model, the RMSE values of LSTM (Long Short Term Memory) with a single function of weight price are 8.719 and 13.759, and the RESM values of prediction results are larger than those of other models, so the accuracy of prediction results is higher.


LSTM; Neural Network; Time series

Cite This Paper

Zibin Bi, Ruixuan Hao, Ziqi Dai. Predict the Price Change over Time with LSTM Neural Network. Academic Journal of Business & Management (2022) Vol. 4, Issue 4: 79-82. https://doi.org/10.25236/AJBM.2022.040416.


[1] Lee CC, Zeng J H. Revisiting the relationship between spot and futures oil prices: Evidence from quantile cointegrating regression. Energy Economics [J], 2011, 33(5): 924-935. 

[2] Schweikert K. Are gold and silver cointegrated? New evidence from quantile cointegrating regressions. Journal of Banking and Finance [J], 2018, 88: 44-51. 

[3] Ghysels E, Santa-Clara P, Valkanov R. There is a risk-return tradeoff after a11. Journal of Financial Economics [J], 2005, 76(3): 509-548. 

[4] HUANG Zhehao, LI Zhenghui, DONG Hao. Research on the Yield Distribution Characteristics of Virtual Financial Assets: A Case Study of Bitcoin [J]. System Journal of Science and Mathematics, 20 1 8, 38(04): 468-483.

[5] Xu Qi, Zuo Junqing, Jiang Cuixia. Time-varying portfolio investment decision based on DCC-MIDAS and parametric strategy [J]. System Journal of Unified Science and Mathematics, 2018, 38(04): 438-455.

[6] LIU Han, LIU Jinquan. Real-time forecasting and short-term forecasting of China's macroeconomic aggregates-forecasts based on mixed frequency data Chapter 38 Empirical Analysis An empirical study of the model. Economic Research [J], 2011, 3: 4.17. 

[71 Zheng Tingguo, Shang Yuhuang. Stock market volatility measurement and forecasting based on macro fundamentals.World Economy [J], 2014, 12: 118.139. 

[8] Liu Jinquan, Liu Han, Yin Zhong. Application of Macroeconomic Mixing Data Model in China: An Empirical Evidence Based on MIDAS Model study. Economic Science [J], 2010, 5: 23.34.

[9] Zhou Decai, Zhu Zhiliang, Ji Yingxin, Yu Yonglei. Compilation and Application Of Mixed Asymmetric Financial Prosperity Index——Based on Empirical Analysis of MF-MS-DFM Model [J]. Management Review, 2019, 3l (8): 71.83. 

[10] GhyselsE, Santa—Clara P’ValkanovbR. There is a risk. return tradeoff after a11. Journal of Financial Economics [J]. 2005, 76(3): 509548. 

[11] Ghysels E, Plazzi A, Valkanov R. Why invest in emerging markets? The role of conditional return asymmetry. The Journal of Finance [J], 2016, 71(5): 2145-2192.

[12] Koenker R Bassett J G. Regression quantiles. Journal of the Econometric Society [J] 1978, 46: 33.50