Proceedings of the 4th International Conference on Economic Management and Big Data Applications, ICEMBDA 2023, October 27–29, 2023, Tianjin, China

Research Article

Automated Digital Currency Trading Algorithm Based on LSTM Neural Networks

Download32 downloads
  • @INPROCEEDINGS{10.4108/eai.27-10-2023.2341947,
        author={Wandong  Zhai},
        title={Automated Digital Currency Trading Algorithm Based on LSTM Neural Networks},
        proceedings={Proceedings of the 4th International Conference on Economic Management and Big Data Applications, ICEMBDA 2023, October 27--29, 2023, Tianjin, China},
        publisher={EAI},
        proceedings_a={ICEMBDA},
        year={2024},
        month={1},
        keywords={lstm neural network; automatic trading algorithm; digital currency; computer simulation},
        doi={10.4108/eai.27-10-2023.2341947}
    }
    
  • Wandong Zhai
    Year: 2024
    Automated Digital Currency Trading Algorithm Based on LSTM Neural Networks
    ICEMBDA
    EAI
    DOI: 10.4108/eai.27-10-2023.2341947
Wandong Zhai1,*
  • 1: Beijing Jiaotong University
*Contact email: 20711032@bjtu.edu.cn

Abstract

Aiming at the problem that the price trend of financial products is affected by many factors with high noise, and it is difficult to accurately grasp the best time to buy and sell digital currencies under the interference of commissions, this paper proposes a set of automatic trading algorithms based on the LSTM neural network model, which can predict the future price of digital currencies under the conditions of appreciation and depreciation trends, and based on the trend analysis strategy, it can automatically determine the best time to buy and sell, and give the same-day buy or sell reasonable recommendations. Subsequently, this paper uses the tushare financial data interface package to obtain the daily gold bitcoin price of bitcoin from 2016 to 2021, a total of 1,826 data, and uses this data to conduct simulated trading, and the results of the computer-simulated trading shows that the algorithm can accurately capture the upward and downward trends of digital currencies, and carry out accurate trading strategy judgments and revenue optimization of the automatic trading.