Skip to main content
AI × Quant × TradingFoundations US$99 · Signals US$1,299 · AI Live US$5,980 · partner institution employees firstView →
arXiv q-fin· Arshia Abolghasemi, Seyed Reza Tavakoli, Parsa Naderi, Nazanin Mirzaei, Behrad Jahani, Saba Yousefzadeh, Tahereh Javaheri, Mohammad Hosein Rohban, Gholamali Aminian, Ali Habibnia·· 5 hr agoAI Score54

StochLOB: Robust Limit Order Book Trend Prediction via Heavy-Tailed Score Matching

StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction

AI summary

An arXiv paper proposes the STOCHLOB training-specific score matching framework, which replaces Gaussian Brownian noise in diffusion forward perturbation with jump Lévy noise from compound Poisson variance mixtures and truncated α-stable noise from positive stable Gaussian scale mixtures, while still using a deterministic predictor during inference.

Source:arXiv q-fin · arxiv.org

Next steps

Research Column: Backtesting and ValidationWhy backtests look good but fail in live trading, and how to conduct out-of-sample testing.WeChat Community and Contact InformationView official contact details; QR codes will be displayed on the About page once available.Prefer English? Get the research briefing by emailRegister your interest in English research updates on our website.