Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19–21, 2023, Hangzhou, China

Research Article

Quantitative Investment Model Based on Bidirectional LSTM

Download69 downloads
  • @INPROCEEDINGS{10.4108/eai.19-5-2023.2334234,
        author={Sijia  Chen},
        title={Quantitative Investment Model Based on Bidirectional LSTM},
        proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China},
        publisher={EAI},
        proceedings_a={ICBBEM},
        year={2023},
        month={7},
        keywords={quantitative investment; bidirectional lstm; integrated learning},
        doi={10.4108/eai.19-5-2023.2334234}
    }
    
  • Sijia Chen
    Year: 2023
    Quantitative Investment Model Based on Bidirectional LSTM
    ICBBEM
    EAI
    DOI: 10.4108/eai.19-5-2023.2334234
Sijia Chen1,*
  • 1: Wuhan University of Technology
*Contact email: chensijia@whut.edu.cn

Abstract

With the development of big data technology, quantitative investment has become more and more important in the global financial trading market. To discuss the price prediction effects of different machine learning methods under the unit of trading time of minutes, three models based on integration learning, LSTM and bidirectional LSTM are developed in this paper. To evaluate the effectiveness of each model, this paper uses historical data of opening price, closing price, high price, low price, volume and amount for every 5 minutes from July 14, 2021 to January 28, 2022 in China's A-share market, and takes VMA, VMACD, BBI, MA, EXPMA and other indicators with strong correlation with volume and closing price for model construction and backtest analysis, and The regression prediction effect of the model is evaluated by the goodness-of-fit and other indicators. Finally, it is evaluated that the bidirectional LSTM-based time series forecasting model is better in predicting the volume every 5 minutes and can assist investors in making minute-based buy-sell decisions.