面向数字货币量化交易的OAC模型研究

许波; 贺一峻; 李祥霞

doi:10.11959/j.issn.2096-6652.202402

您当前的位置：

首页 >

文章列表页 >

面向数字货币量化交易的OAC模型研究

学术论文 | 更新时间：2024-08-06

- 面向数字货币量化交易的OAC模型研究
- Research on OAC model for quantitative trading of digital currency
- 智能科学与技术学报 2024年6卷第2期页码：220-231
- 作者机构：
  
  1.广东财经大学信息学院，广东广州 510320
  2.广东省智能商务工程技术研究中心，广东广州 510320
- 作者简介：
  
  [ "许波（1982- ），男，博士，广东财经大学副教授、硕士生导师，CCF高级会员，主要研究方向为机器学习、量化交易。" ]
  [ "贺一峻（1998- ），男，广东财经大学硕士生，CCF学生会员，主要研究方向为机器学习、量化交易。" ]
  [ "李祥霞（1988- ），女，博士，广东财经大学讲师、硕士生导师，主要研究方向为机器学习、深度学习等。" ]
- 基金信息：
  
  广东省哲学社会科学规划项目(GD24CGL08);广东省普通高校重点领域专项(2021ZDZX3006);广州市科技计划项目(202201011651)
- DOI：10.11959/j.issn.2096-6652.202402
  中图分类号： TP399
- 收稿：2023-10-21，
  
  修回：2024-02-05，
  
  纸质出版：2024-06-15
- 稿件说明：
移动端阅览
许波,贺一峻,李祥霞.面向数字货币量化交易的OAC模型研究[J].智能科学与技术学报,2024,06(02):220-231.

XU Bo,HE Yijun,LI Xiangxia.Research on OAC model for quantitative trading of digital currency[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):220-231.
许波,贺一峻,李祥霞.面向数字货币量化交易的OAC模型研究[J].智能科学与技术学报,2024,06(02):220-231. DOI： 10.11959/j.issn.2096-6652.202402.

XU Bo,HE Yijun,LI Xiangxia.Research on OAC model for quantitative trading of digital currency[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):220-231. DOI： 10.11959/j.issn.2096-6652.202402.

摘要

针对数字货币量化交易中存在的问题，即大量且复杂因子以及因子状态空间维度较高，导致交易模型制定策略的准确性和风险控制能力难以兼顾，提出了一种改进的OAC模型——OAC_LSTM_ATT。该模型采用了LSTM和多头注意力机制来优化OAC的网络结构，从而提高OAC对时间序列数据的建模能力和泛化能力。通过这种融合，智能体在量化交易环境中可以更加灵活和准确地做出交易决策，进一步提高交易策略的质量和效果。实验结果显示，在比特币市场中，累计收益率达到了16.36%，最大回撤率为9.08%，夏普比为0.014，波动率为13.09%。在以太坊市场中，对应的指标为16.30%、8.56%、0.014和13.42%。与PPO、LSTM_PPO和A2C等模型相比，OAC_LSTM_ATT在有效性和稳定性方面具有一定优势，为量化交易策略制定提供了有价值的参考。

Abstract

In response to the challenges encountered in quantitative trading of digital currencies

characterized by the presence of a multitude of intricate factors and a high-dimensional factor state space

an enhanced optimistic actor-critic(OAC) model

referred to as OAC_LSTM_ATT

had been proposed. This model incorporated long short-term memory (LSTM) and a multi-head attention mechanism to optimize the network architecture of OAC

thereby augmenting its capacity for modeling time-series data and generalization. Through this integration

the intelligent agent operating in the quantitative trading environment was capable of making more adaptable and precise trading decisions

consequently elevating the quality and efficacy of trading strategies. Experimental findings revealed that

in the Bitcoin market

the cumulative return achieved was 16.36%

with a maximum drawdown of 9.08%

a Sharpe ratio of 0.014

and a volatility of 13.09%. Corresponding metrics in the Ethereum market amounted to 16.30%

8.56%

0.014

and 13.42%. When compared to models such as PPO

LSTM_PPO

A2C

OAC_LSTM_ATT demonstrates superior performance in terms of both effectiveness and stability

thereby offering valuable insights for the development of quantitative trading strategies.

关键词

Keywords

references

XIA H S, GAO Y M, ZHANG J Z. Understanding the adoption context of China's digital currency electronic payment[J]. Financial Innovation, 2023, 9(1): 63.

BENSAïDA A. The linkage between Bitcoin and foreign exchanges in developed and emerging markets[J]. Financial Innovation, 2023, 9(1): 38.

FANG F, VENTRE C, BASIOS M, et al. Cryptocurrency trading: a comprehensive survey[J]. Financial Innovation, 2022, 8(1): 13.

MCNALLY S, ROCHE J, CATON S. Predicting the price of Bitcoin using machine learning[C]//Proceedings of the 2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP). Piscataway: IEEE Press, 2018: 339-343.

WU C H, LU C C, MA Y F, et al. A new forecasting framework for Bitcoin price with LSTM[C]//Proceedings of the 2018 IEEE International Conference on Data Mining Workshops (ICDMW). Piscataway: IEEE Press, 2018: 168-175.

章盼. 基于GRU的加密货币价格趋势预测[D]. 湘潭: 湘潭大学, 2019.

ZHANG P. Cryptocurrency price trend prediction based on GRU[D]. Xiangtan: Xiangtan University, 2019.

柯坤锋. 基于深度学习的比特币价格预测研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.

KE K F. Research on bitcoin price prediction based on deep learning[D].Harbin: Harbin Institute of Technology, 2020.

HUA Y Q. Bitcoin price prediction using ARIMA and LSTM[J]. E3S Web of Conferences, 2020, 218: 01050.

荆鹏霏. 基于多模型的比特币价格预测对比研究[D]. 太原: 山西大学, 2021.

JING P F. A comparative study of Bitcoin price prediction based on multiple models [D]. Taiyuan: Shanxi University, 2021

曾凡成. 基于深度学习方法和分位数回归的加密货币价格预测研究[D]. 南昌: 江西财经大学, 2021.

ZENG F C. Research on cryptocurrency price prediction based on deep learning method and quantile regression[D]. Nanchang: Jiangxi University of Finance and Economics, 2021.

郭思涵. 基于改进循环神经网络的比特币价格预测及交易策略研究[D]. 上海: 上海师范大学, 2021.

GUO S H. Research on Bitcoin price forecasting and trading strategy based on improved cyclic neural network[D]. Shanghai: Shanghai Normal University, 2021.

AWOKE T, ROUT M, MOHANTY L, et al. Bitcoin price prediction and analysis using deep learning models[M]//SATAPATHY S C, BHATEJA V, RAMAKRISHNA MURTY M, et al. Communication Software and Networks. Singapore: Springer, 2021: 631-640.

AKYILDIRIM E, CEPNI O, CORBET S, et al. Forecasting mid-price movement of Bitcoin futures using machine learning[J]. Annals of Operations Research, 2023, 330(1): 553-584.

CHEN T H, CHEN M Y, DU G T. The determinants of Bitcoin's price: utilization of GARCH and machine learning approaches[J]. Computational Economics, 2021, 57(1): 267-280.

RANJAN S, KAYAL P, SARAF M. Bitcoin price prediction: a machine learning sample dimension approach[J]. Computational Economics, 2023, 61(4): 1617-1636.

CARAPUÇO J, NEVES R, HORTA N. Reinforcement learning applied to Forex trading[J]. Applied Soft Computing Journal, 2018, 73: 783-794.

宋稳柱. 数字货币投资组合策略研究: 基于深度强化学习方法[D]. 南京: 南京信息工程大学, 2019.

SONG W Z. Research on digital currency portfolio strategy [D]. Nanjing: Nanjing University of Information Science & Technology, 2019.

李尚宜. 基于深度强化学习的金融交易算法实证研究[D]. 南京: 东南大学, 2019.

LI S Y. An empirical research on financial trading algorithm based on deep reinforcement learning[D]. Nanjing: Southeast University, 2019.

熊礼东. 基于深度强化学习的量化交易研究[D]. 成都: 电子科技大学, 2019.

XIONG L D. Research on quantitative trading based on deep reinforcement learning[D]. Chengdu: University of Electronic Science and Technology of China, 2019.

ZHANG Z H, ZOHREN S, ROBERTS S. Deep reinforcement learning for trading[J]. The Journal of Financial Data Science, 2020, 2(2): 25-40.

SULIMAN U, VAN ZYL T L, PASKARAMOORTHY A. Cryptocurrency trading agent using deep reinforcement learning[C]//Proceedings of the 2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI). Piscataway: IEEE Press, 2022: 6-10.

许杰, 祝玉坤, 邢春晓. 基于深度强化学习的金融交易算法研究[J]. 计算机工程与应用, 2022, 58(7): 276-285.

XU J, ZHU Y K, XING C X. Research on financial trading algorithm based on deep reinforcement learning[J]. Computer Engineering and Applications, 2022, 58(7): 276-285.

CUI T X, DING S S, JIN H, et al. Portfolio constructions in cryptocurrency market: a CVaR-based deep reinforcement learning approach[J]. Economic Modelling, 2023, 119: 106078.

CHEN X M, GUO H R. A futures quantitative trading strategy based on a deep reinforcement learning algorithm[C]//Proceedings of the 2023 IEEE 8th International Conference on Big Data Analytics (ICBDA). Piscataway: IEEE Press, 2023: 175-179.

XIAO X C. Quantitative investment decision model based on PPO algorithm[J]. Highlights in Science, Engineering and Technology, 2023, 34: 16-24.

SHIN H G, JEONG S, KIM E Y, et al. Synergistic formulaic alpha generation for quantitative trading based on reinforcement learning [EB]. arXiv preprint, 2024, arXiv: 2401.02710

FU K, YU Y D, LI B. Multi-feature supervised reinforcement learning for stock trading[J]. IEEE Access, 2023, 11: 77840-77855.

项凤涛, 罗俊仁, 谷学强, 等. 群视角下的多智能体强化学习方法综述[J]. 智能科学与技术学报, 2023, 5(3): 313-329.

XIANG F T, LUO J R, GU X Q, et al. Survey on multi-agent reinforcement learning methods from the perspective of population[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 313-329.

HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB]. arXiv preprint, 2017, arXiv: 1706.03762.

CIOSEK K, VUONG Q, LOFTIN R, et al. Better exploration with optimistic actor-critic[EB]. arXiv preprint, 2019, arXiv: 1910.12807.

SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[EB]. arXiv preprint, 2017, arXiv: 1707.06347.

贺俊杰, 张洁, 张朋, 等. 基于长短期记忆近端策略优化强化学习的等效并行机在线调度方法[J]. 中国机械工程, 2022, 33(3): 329-338.

HE J J, ZHANG J, ZHANG P, et al. Related parallel machine online scheduling method based on LSTM-PPO reinforcement learning[J]. China Mechanical Engineering, 2022, 33(3): 329-338.

MNIH V, BADIA A P, MIRZA M, et al. Asynchronous methods for deep reinforcement learning[C]//Proceedings of the 33rd International Conference on Machine Learning(ICML). New York: ACM, 2016:1928-1937.

浏览量

319

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

深度强化学习应用于金融市场量化交易研究综述

基于KPPO算法的四旋翼无人机飞行控制

人工智能与量化交易的课程建设

基于双池DQN的HVAC无模型优化控制方法

基于TD3的电动汽车复合电源能量管理策略研究