Metraipolis › archive › dc_ad747fe4bfcc

Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting — arXiv:2608.12259

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12259
License (as archived): CC0-1.0
Archived: 2026-10-19T05:40:06.354Z
SHA-256 of the archived text: ed83d489bdcf0f81261704a13b550cab15df9dd2cfb2f722cef4f7b3fa35cd99
Stable URL of this page: https://metraipolis.com/documento/dc_ad747fe4bfcc

How to cite

Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting — arXiv:2608.12259 — arXiv (en), https://arxiv.org/abs/2608.12259 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad747fe4bfcc (Metraipolis archive dc_ad747fe4bfcc, sha256 ed83d489bdcf0f81261704a13b550cab15df9dd2cfb2f722cef4f7b3fa35cd99)

BibTeX

@misc{dcad747fe4bfcc,
  title = {Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting — arXiv:2608.12259},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12259},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad747fe4bfcc; sha256 ed83d489bdcf0f81261704a13b550cab15df9dd2cfb2f722cef4f7b3fa35cd99},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12259. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Post-training quantization (PTQ) enables such deployment without retraining. However, reliable activation quantization requires calibration: activation ranges are estimated from historical data before deployment and then remain fixed during future inference. The importance of this deployment choice for financial forecasting remains poorly understood. We present a systematic study of activation calibration for PTQ in cross-sectional volatility forecasting on the S&P 500. Our evaluation covers seven representative neural architectures, eight walk-forward test years (2018-2025), and 560 trained models. We find that activation calibration has little effect at 8 bits but becomes the primary determinant of predictive performance at 4 bits. Under default absolute-maximum (abs-max) calibration, static 4-bit quantization of both weights and activations removes 11-62% of the full-precision mean information coefficient in affected architectures. Replacing abs-max with percentile calibration recovers 53-94% of this degradation in the four most affected architectures. The preferred activation range also varies across market periods. Narrow ranges improve resolution under typical market conditions but lose part of their advantage when test-period market dispersion exceeds the calibration history. These findings show that activation calibration is a first-class deployment decision for reliable 4-bit PTQ in financial forecasting. When substantial degradation remains, 8-bit activations or weight-only 4-bit quantization provide more robust deployment choices.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Statistical Finance (q-fin.ST).
Pagina del lavoro: https://arxiv.org/abs/2608.12259 — 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 2026-10-19T05:18:32.511Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).