Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, Nanjing, China

Research Article

Financial Asset Volatility Forecasting using LSTM with Intraday High-Low Price Information

Download173 downloads
  • @INPROCEEDINGS{10.4108/eai.26-5-2023.2334349,
        author={Yaohui  Bai and Ping  Bai and Xinyan  Zhang and Huayang  Li},
        title={Financial Asset Volatility Forecasting using LSTM with Intraday High-Low Price Information},
        proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China},
        publisher={EAI},
        proceedings_a={MSEA},
        year={2023},
        month={7},
        keywords={volatility forecasting garch lstm financial asset high-low price},
        doi={10.4108/eai.26-5-2023.2334349}
    }
    
  • Yaohui Bai
    Ping Bai
    Xinyan Zhang
    Huayang Li
    Year: 2023
    Financial Asset Volatility Forecasting using LSTM with Intraday High-Low Price Information
    MSEA
    EAI
    DOI: 10.4108/eai.26-5-2023.2334349
Yaohui Bai1,*, Ping Bai2, Xinyan Zhang1, Huayang Li1
  • 1: Jiangxi University of Finance and Economics
  • 2: Library of Jiangxi University of Finance and Economics
*Contact email: baiyaohui@jxufe.edu.cn

Abstract

In recent years, predicting the volatility of financial assets has received increasing attention due to the continuous development and increased volatility of financial markets. In this paper, we propose a volatility prediction model based on the Long Short-Term Memory (LSTM) model in deep learning, which considers the intraday high and low prices in financial asset sequences. To compare the performance of the proposed model, we also use the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model for comparison. By analyzing the data of the Shanghai Composite Index from January 1, 2015 to December 31, 2019, the results show that the proposed model outperforms the GARCH model, which is also reflected in the root-mean-square error of the two models. The proposed method exhibits promising results in predicting asset volatility and highlights the potential of LSTM models in the field of financial asset volatility prediction.