Metraipolis › archive › dc_ca4019eb433c

WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion — arXiv:2609.14733

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14733
License (as archived): CC0-1.0
Archived: 2026-10-16T00:11:00.341Z
SHA-256 of the archived text: d8187da52b71c04b0fbaa619e2f0031853c48ced77b5077181409e1064c9829c
Stable URL of this page: https://metraipolis.com/documento/dc_ca4019eb433c

How to cite

WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion — arXiv:2609.14733 — arXiv (en), https://arxiv.org/abs/2609.14733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca4019eb433c (Metraipolis archive dc_ca4019eb433c, sha256 d8187da52b71c04b0fbaa619e2f0031853c48ced77b5077181409e1064c9829c)

BibTeX

@misc{dcca4019eb433c,
  title = {WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion — arXiv:2609.14733},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14733},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca4019eb433c; sha256 d8187da52b71c04b0fbaa619e2f0031853c48ced77b5077181409e1064c9829c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Statistical Finance (q-fin.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.14733 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.712Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).