Newest papers

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

Jung Hun Phee, Tucker Balch · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.22727 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Estudiamos la distribución condicional del volumen de orden límite presentado durante los próximos cinco minutos, dado el libro de pedidos actual y el flujo de pedidos recientes. La tarea requiere capturar la colocación del precio, el volumen total y la incertidumbre predictiva conjuntamente. Las pérdidas de difusión de forma coordinada no cuentan explícitamente con el desplazamiento del precio, mientras que la normalización de los campos de la masa de la unidad elimina la información sobre el volumen total. El acuerdo sobre las estadísticas de resumen seleccionadas también no establece fidelidad a la distribución de campo conjunto. Introducimos OrderFlowDiT, un transformador de difusión condicional para la oferta no normalizada y los campos de volumen a precio, entrenados con una pérdida auxiliar no equilibrada de transporte óptimo (UOT). También

Machine translation (Meta M2M100); the English original follows.

Abstract

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Scoring rule, Computer science, Probabilistic logic, Calibration, Bayesian probability, Joint probability distribution

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange