AI 中文总结
针对金融时间序列非平稳性，提出制度感知动态窗口化框架，将市场制度信号融入Transformer，在五只标普500股票上提升预测性能与可解释性。
AI 中文摘要
金融时间序列表现出非平稳行为，其中时间依赖性的强度和范围随市场制度而变化。趋势性、低波动性阶段通常需要长距离上下文信息，而均值回归、高波动性时期则更依赖于短期动态。具有固定注意力窗口和静态位置编码的标准Transformer架构因此无法适应此类变化。在本工作中，我们提出了一种制度感知的动态窗口化框架，将市场制度信息直接整合到Transformer中。我们从价格序列中构建了四个通用制度信号：波动率比率、趋势强度、局部可预测性比率（LPR）和滚动自相关。我们通过两种机制将这些信号纳入模型：（i）将制度增强输入到标准Transformer架构中，以及（ii）一种修改后的注意力层，使用制度嵌入来调节注意力权重。在五只标普500股票上的实验显示，在五个评估指标上均取得了一致的改进，表明制度感知的动态窗口化增强了金融预测任务中的可解释性和预测性能。
英文摘要
Financial time series exhibit non-stationary behavior, where the strength and extent of temporal dependencies vary across market regimes. Trending, low-volatility phases typically require long-range contextual information, whereas mean-reverting, high-volatility periods rely more heavily on short-term dynamics. Standard Transformer architectures, with fixed attention windows and static positional encodings, are therefore unable to adapt to such variations. In this work, we propose a regime-aware dynamic windowing framework that incorporates market regime information directly into the Transformer. We construct four generic regime signals from price series: volatility ratio, trend strength, local predictability ratio (LPR), and rolling autocorrelation. We incorporate these signals into the model through two mechanisms: (i) regime-augmented inputs to a standard Transformer architecture, and (ii) a modified attention layer that modulates attention weights using regime embeddings. Experiments on five S&P 500 stocks show consistent improvements across five evaluation metrics, demonstrating that regime-aware dynamic windowing enhances both interpretability and predictive performance in financial forecasting tasks.
