Metraipolis › archive › dc_2343bcd3ce8f

OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting — arXiv:2610.22727

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22727
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:57.692Z
SHA-256 of the archived text
215350ff8508fc5c67e90ecd1c40e803f794bdb48b88ed82885b099b48e8d071
Stable URL of this page
https://metraipolis.com/documento/dc_2343bcd3ce8f

How to cite

OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting — arXiv:2610.22727 — arXiv (en), https://arxiv.org/abs/2610.22727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2343bcd3ce8f (Metraipolis archive dc_2343bcd3ce8f, sha256 215350ff8508fc5c67e90ecd1c40e803f794bdb48b88ed82885b099b48e8d071)
BibTeX
@misc{dc2343bcd3ce8f,
  title = {OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting — arXiv:2610.22727},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22727},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2343bcd3ce8f; sha256 215350ff8508fc5c67e90ecd1c40e803f794bdb48b88ed82885b099b48e8d071},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the conditional distribution of limit-order volume submitted over the next five minutes, given the current order book and recent order flow. The task requires capturing price placement, total volume, and predictive uncertainty jointly. Coordinate-wise diffusion losses do not explicitly account for price displacement, while normalizing fields to unit mass removes information about total volume. Agreement on selected summary statistics also does not establish fidelity to the joint field distribution. We introduce OrderFlowDiT, a conditional Diffusion Transformer for unnormalized bid and ask volume-at-price fields, trained with an unbalanced optimal-transport (UOT) auxiliary loss. We also develop a full-field evaluation framework that combines a transport cost sensitive to price placement and total volume with proper scoring rules and calibration diagnostics. In the primary comparison on 1950 validation conditions across 30 U.S. equities, adding UOT reduces full-field transport cost by 45.8% and the transport energy score by 26.1% relative to training with mean squared error alone. Both measures improve for every stock. These findings support incorporating price geometry and volume into generative modeling, with field accuracy and predictive uncertainty evaluated together.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Trading and Market Microstructure (q-fin.TR).
Pagina del lavoro: https://arxiv.org/abs/2610.22727 — 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 2026-10-19T08:39:10.123Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).