发表机构
Indian Institute of Technology Jodhpur（印度理工学院焦特布尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
WaVeFuse提出双分支架构，结合小波去噪、通道级CWT与垂直注意力融合，实现自适应股指预测，在多个市场取得高精度和稳健性。
AI 中文摘要
用于股指预测的混合深度学习受限于三个问题：OHLCV噪声向派生技术指标（TIs）的传播、不分通道的多尺度分解混淆了异质频率特征，以及无法适应市场机制转变的静态多分支融合。WaVeFuse通过统一的双分支架构解决了这些局限性。Symlet-4小波去噪（第2层，MAD软阈值）抑制了OHLCV中的微观结构噪声。从去噪价格计算的七个低滞后技术指标由因果通道级连续小波变换（Morlet，32个尺度）编码为每时间步的尺度空间矩阵。CNN-BiLSTM分支捕获时间动态，而双层Transformer（头数=4，dk∈{16,32}）建模尺度间频谱依赖，其表示通过2令牌softmax门控垂直注意力融合（VAF）集成，该融合在市场机制转变时动态重新加权各分支。在KOSPI、DAX、NYSE综合指数和Russell 2000（2010-2023）上采用前向验证（WFV）评估，WaVeFuse实现了R²=0.81-0.96和方向准确率70.5-78.3%。在十二个数据集-期间配置中，其MAE优于七个最先进模型8.9-20.2%。Diebold-Mariano统计量（4.62-10.38，p<0.001）确认了在四个指数上相对于调优良好的XGBoost基准的优越性。消融研究验证了各组成部分的贡献。在考虑10个基点交易成本的实际回测中，WaVeFuse的方向策略在四个市场上实现了平均夏普比率3.69，并在COVID-19崩盘期间将最大回撤限制在7.5%。凭借152k参数（0.68MB）和低于1.3毫秒的GPU推理时间，WaVeFuse提供了一个计算高效、机制稳健的框架，适用于研究和决策支持部署。
英文摘要
Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts. WaVeFuse addresses these limitations through a unified dual-branch architecture. Symlet-4 wavelet denoising (level 2, MAD soft threshold) suppresses microstructure noise in OHLCV. Seven low-lag TIs computed from denoised prices are encoded by a causal channel-wise continuous wavelet transform (Morlet, 32 scales) into a per-timestep scale-space matrix. A CNN-BiLSTM branch captures temporal dynamics, while a dual-layer Transformer (heads=4, dk in {16, 32}) models inter-scale spectral dependencies, and their representations are integrated by a 2-token softmax gate Vertical Attention Fusion (VAF) that dynamically reweights branches as market regimes shift. Evaluated under walk-forward validation (WFV) on KOSPI, DAX, NYSE Composite, and Russell 2000 (2010-2023), WaVeFuse achieves R2 = 0.81-0.96 and directional accuracy 70.5-78.3%. It outperforms seven state-of-the-art models by 8.9-20.2% MAE across twelve dataset-period configurations. Diebold-Mariano statistics (4.62-10.38, p<0.001) confirm superiority over a well-tuned XGBoost benchmark across four indices. Ablation verifies component-wise contributions. Under realistic backtesting with 10 basis point transaction costs, WaVeFuse's directional strategy achieves a mean Sharpe ratio of 3.69 across four markets and limits maximum drawdown to 7.5% during the COVID-19 crash. With 152k parameters (0.68MB) and sub-1.3ms GPU inference, WaVeFuse delivers a computationally efficient, regime-robust framework suitable for research and decision-support deployment.
Comments40 pages, 13 Figures, 15 Tables, Preprint, Under Review
