发表机构
University of Maryland, College Park（马里兰大学帕克分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究通过信号-预测-系统诊断框架，发现短期波动率预测中统计残差简化（方差降低约82%）并不改善残差LSTM的预测精度（MSE从0.3049升至0.3594），揭示了预测器-预处理器不对称性。
AI 中文摘要
混合统计-神经管道通常假设成功的统计第一阶段会留下更干净、更易学习的残差目标。我们通过信号-预测-系统诊断框架，在短期波动率预测中检验了这一假设。在五种流动性强的美国资产中，与波动率对齐的HAR风格模型优于AR、MA和ARIMA。在扩展的训练窗口内，用于构建残差LSTM序列的预标准化拟合残差过程，其方差比相应目标低约82%，且滞后1阶自相关接近零；独立地，滚动伪样本外HAR误差显示约74%的方差减少和同样弱的滞后1阶依赖性。然而，仅残差的LSTM增强平均将均方误差从0.3049提高到0.3594，且每种资产均出现恶化。纯LSTM记录了最低的选定伪样本外MSE，为0.2649，而残差混合模型需要显著更长的端到端运行时间且未提高准确性。我们将此模式描述为预测器-预处理器不对称性：第一阶段预测成功和统计残差简化不一定转化为有用的下游神经预处理。
英文摘要
Hybrid statistical-neural pipelines often assume that a successful statistical first stage leaves a cleaner and more learnable residual target. We examine that assumption in short-horizon volatility forecasting through a signal-forecast-system diagnostic framework. Across five liquid U.S. assets, a volatility-aligned HAR-style model outperforms AR, MA, and ARIMA. Within expanding training windows, the pre-standardization fitted residual process used to construct residual-LSTM sequences has about 82% lower variance than the corresponding target and near-zero lag-1 autocorrelation; independently, rolling pseudo-out-of-sample HAR errors show about 74% variance reduction and similarly weak lag-1 dependence. Residual-only LSTM augmentation nevertheless raises mean squared error from 0.3049 to 0.3594 on average, with deterioration on every asset. Pure LSTM records the lowest selected pseudo-out-of-sample MSE, 0.2649, while the residual hybrid requires substantially more end-to-end runtime without improving accuracy. We describe this pattern as forecaster-preconditioner asymmetry: first-stage forecasting success and statistical residual simplification need not translate into useful downstream neural preconditioning.
CommentsAccepted at the 10th Computational Methods in Systems and Software (CoMeSySo 2026). 17 pages, 4 figures
