VertiFuseX：通过多流时间融合实现可泛化的金融预测
VertiFuseX: Generalizable Financial Forecasting via Multi-Stream Temporal Fusion
- 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总结：
VertiFuseX提出一种混合LSTM架构，通过倒数第二层垂直融合多尺度时间表示，在固定超参数下提升金融预测的准确性和泛化能力，显著降低预测误差并支持轻量部署。
AI中文摘要：
股票价格预测因金融时间序列的非平稳性和噪声特性而仍然具有挑战性。现有的深度学习模型通常依赖于僵化的决策级融合、临时性的超参数调整以及压缩的最终层输出，导致信息丢失、过拟合以及跨市场泛化能力受限。我们提出了VertiFuseX，一种混合LSTM架构，使用多尺度时间表示的倒数第二层垂直融合。VertiFuseX堆叠并重新加权来自LSTM、Bi-LSTM和St-LSTM分支的倒数第二层特征，集成一个并行DNN流，并在固定超参数配置下通过反向传播联合优化所有组件。这保留了跨尺度的更丰富的中间时间信息。在2010年至2024年15年间10个全球股票指数的收盘价上，使用严格的时间顺序样本外测试并保留最后365个交易日，VertiFuseX相较于基于LSTM的基线实现了30-54%的MAPE降低以及超过40%的MAE和RMSE改进，并在33项指标-数据集比较中优于七个最先进的模型。消融研究证实，倒数第二层融合相较于最终层融合和决策级集成带来了这些增益。基于梯度的显著性分析显示，在9-15天的滞后中，对中期依赖关系的一致强调。通过极端市场制度下的算法交易模拟进行的经济验证显示，最大回撤减少和风险调整后收益更优。凭借675k参数、2.6 MB内存占用和1.5 ms/样本推理延迟，VertiFuseX为稳健的金融预测提供了一个轻量级、可解释、可部署的框架。
英文摘要：
Stock price prediction remains challenging due to the non-stationary and noisy nature of financial time series. Existing deep learning models often rely on rigid decision-level fusion, ad hoc hyperparameter tuning, and compressed final-layer outputs, causing information loss, overfitting, and limited cross-market generalization. We propose VertiFuseX, a hybrid LSTM architecture using penultimate-layer vertical fusion of multi-scale temporal representations. VertiFuseX stacks and reweights penultimate features from LSTM, Bi-LSTM, and St-LSTM branches, integrates a parallel DNN stream, and jointly optimizes all components via backpropagation under a fixed hyperparameter configuration. This preserves richer intermediate temporal information across scales. Evaluated on 15 years (2010-2024) of closing prices from 10 global equity indices using strict chronological out-of-sample testing with the final 365 trading days held out, VertiFuseX achieves 30-54% MAPE reductions and over 40% improvements in MAE and RMSE versus LSTM-based baselines, and outperforms seven state-of-the-art models across 33 metric-dataset comparisons. Ablation studies confirm penultimate-layer fusion drives these gains over final-layer fusion and decision-level ensembling. Gradient-based saliency analysis shows consistent emphasis on mid-range dependencies at lags 9-15 days. Economic validation via algorithmic trading simulation under extreme market regimes shows reduced maximum drawdowns and superior risk-adjusted returns. With 675k parameters, a 2.6 MB memory footprint, and 1.5 ms/sample inference latency, VertiFuseX offers a lightweight, interpretable, deployment-ready framework for robust financial forecasting.
