Newest papers

Probabilistic Limit Order Book Forecasting with Conditional Diffusion Models

Junyu Chen, Franklin Liu, Moshu Xu, Lijian Yang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25495 · cited by 0 works (OpenAlex) · open-access PDF

Korean

모델링 제한 간격 주문서 (LOB) 역학은 시장 예측 및 실행 전략 평가에 핵심입니다. 배포 모델은 강력한 실험적 성능을보고 있지만, 기존의 LOB 스냅샷 모델은 일반적으로 학습 된 반복적 인 암호화기 및 공식 통계적 보증을 부족합니다. 우리는 LOBGrad, 확률적 인 LOB 예측을위한 조건부 DDPM 프레임 워크를 도입합니다. 조약적 인 역학하에서 조절 RNN 암호화기와 작업 기반 생성기를 결합합니다. 특히, 우리는 한 단계 DDPM 소음 예측 목표에 대한 과도한 위험 오라클 불평등을 설정합니다. 우리는 확률적 혼합 및 규칙성 가정하에 조건적 인 DDPM 프레임 워크를 도입합니다

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

Abstract

Modeling limit order book (LOB) dynamics is central to market forecasting and execution-strategy evaluation. While diffusion models achieve strong empirical performance, existing LOB snapshot models typically lack a learned recurrent encoder and formal statistical guarantees. We introduce LOBGrad, a conditional DDPM framework for probabilistic LOB forecasting that combines an autoregressive RNN encoder with a diffusion-based generator. In particular, we establish an excess-risk oracle inequality for the one-step DDPM noise-prediction objective under exponential mixing and regularity assumptions. We further show that, under contractive dynamics, the dependence on the conditioning-window length can be reduced to a dependence on the latent-state dimension. Experiments on BTC/USDT, GOOGL, and META show that LOBGrad improves on its encoder-free diffusion ablation across all reported queue metrics and obtains competitive results against other baselines. It also reproduces the key stylized facts of LOB microstructure, and yields reasonably calibrated queue-based predictive intervals. A stylized downstream task illustrates the potential value of the generated forecasts.

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

Topics: Probabilistic logic, Stylized fact, Autoregressive model, Computer science, Gaussian, Statistical model

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