Metraipolis › archive › dc_b27dec47f368

CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting — arXiv:2609.11206

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11206
License (as archived)
CC0-1.0
Archived
2026-10-16T05:23:53.764Z
SHA-256 of the archived text
7b4401bd94689d8b6581e99c7d267da7c7335402a3c5a80618f94a33bbff77ca
Stable URL of this page
https://metraipolis.com/documento/dc_b27dec47f368

How to cite

CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting — arXiv:2609.11206 — arXiv (en), https://arxiv.org/abs/2609.11206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b27dec47f368 (Metraipolis archive dc_b27dec47f368, sha256 7b4401bd94689d8b6581e99c7d267da7c7335402a3c5a80618f94a33bbff77ca)
BibTeX
@misc{dcb27dec47f368,
  title = {CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting — arXiv:2609.11206},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11206},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b27dec47f368; sha256 7b4401bd94689d8b6581e99c7d267da7c7335402a3c5a80618f94a33bbff77ca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cryptocurrency forecasting presents a distinctive combination of extreme cross-asset scale heterogeneity, non-stationary dynamics, and structural dependencies among Open, High, Low, and Close (OHLC) variables. We present CryptoL, a unified framework designed to address these challenges within multivariate time-series forecasting. CryptoL evaluates forecasting error in context-normalized coordinates within the RevIN pipeline, preventing inverse normalization from introducing an additional squared-scale weighting into the MSE objective. We formally characterize this effect through the empirical risk and parameter-gradient geometry, establishing the conditions under which large-scale assets can disproportionately influence shared-model optimization. Beyond loss-space normalization, CryptoL examines channel-independent and channel-dependent normalization for OHLC data, showing that a shared channel-dependent affine transformation preserves candle-order relations that independent channel transformations need not preserve. The framework further incorporates scale-adaptive numerical stabilization to reduce distortions caused by a fixed normalization constant across assets spanning many orders of magnitude, together with a soft feasibility loss that penalizes violations of the defining OHLC inequalities. Experiments across heterogeneous cryptocurrency assets evaluate these components through controlled ablations and demonstrate improvements in forecasting accuracy, training stability, and the frequency of financially valid OHLC predictions relative to the considered baselines. CryptoL therefore provides an integrated approach to scale-balanced optimization, structure-preserving normalization, numerical stabilization, and constraint-aware cryptocurrency forecasting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.11206 — 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 2026-10-16T05:17:51.986Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).