跳至正文
返回文库全部文档

动量 Transformer：可解释的深度学习交易

文章 arXiv papers · 作者: Kieran Wood et al.
阅读原文

总结

本文介绍 Momentum Transformer，这是一种结合注意力机制与LSTM、利用时间序列数据进行交易的混合模型。其注意力机制将模型与更早的时间步相连接，而多个注意力头可表示在不同时间尺度上运行的市场动态。作者将其与基准动量和均值回归策略进行比较，并报告称其表现更好，包括扣除交易成本后。

作者还称，该架构能够适应不断变化的市场环境，并以SARS-CoV-2危机为例。注意力权重可用于查看哪些历史观测值和因素会影响模型决策。摘录未提供数据、实验设计、数值结果，也未说明成本和实施细节，因此仅凭这段描述无法评估所报告表现的强度和普适性。

核心观点

  • 该模型将注意力机制与LSTM结合，把当前预测与更早的时间步相联系。
  • 多个注意力头旨在捕捉不同时间尺度上的市场动态。
  • 作者报告称，与基准动量和均值回归策略相比，该模型表现更好，包括扣除交易成本后。
  • 该模型利用注意力来解释历史观测值和因素的影响。
  • 摘录对评估细节和结果的可迁移性仅提供了有限证据。

标签

机器学习动量均值回归交易执行
全文
# Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture


# Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture









We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM) architectures, which are sequential in nature and tailored to local processing, an attention mechanism provides our architecture with a direct connection to all previous time-steps. Our architecture, an attention-LSTM hybrid, enables us to learn longer-term dependencies, improves performance when considering returns net of transaction costs and naturally adapts to new market regimes, such as during the SARS-CoV-2 crisis. Via the introduction of multiple attention heads, we can capture concurrent regimes, or temporal dynamics, which are occurring at different timescales. The Momentum Transformer is inherently interpretable, providing us with greater insights into our deep-learning momentum trading strategy, including the importance of different factors over time and the past time-steps which are of the greatest significance to the model.

在遵守原作品许可的前提下，附作者信息全文展示。 许可协议: abstract CC0

此摘要由 Stratmill 研究智能体根据原文撰写，并非原文副本。