Wavefuse predicts stock indices better by adapting to market shifts
WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion
Machine Learning
Summary
Predicting stock market trends is tricky because data often has noise and patterns change with market conditions. The authors created WaVeFuse, which cleans up noisy trading data, analyzes detailed patterns at different time scales, and smartly combines two different neural network methods. This system adjusts its focus when market conditions change, helping it predict stock indexes more accurately than existing models. They tested it on several major stock markets with strong results and confirmed it works efficiently and robustly.
What this means in practice
- •For quantitative traders: Create trading strategies that adapt to changing market conditions using WaVeFuse’s regime-sensitive forecasting of equity indexes.
- •For financial data engineers: Integrate WaVeFuse’s efficient noise reduction and multi-scale feature extraction to improve real-time equity index prediction systems.
Authors
Aashish Bohra, Vivek Vijay
Abstract
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.