Paper: arXiv 2610.02917

Authors: David Schaurecker, Lasse B. Strand, Kevin O’Sullivan, Robert Jakob

Abstract

Short-horizon price-trend prediction from limit order books in equity and intraday electricity markets requires models that combine predictive quality with low single-sample latency and a small serialized model size to keep pace with rapid and continuous market updates. We introduce MBOFormer, a 7,203-parameter causal transformer, and MBOFusion, a 14,371-parameter extension with a slow temporal-context branch. Both models process market-by-order (level-3) histories of individual order submissions, cancellations, and executions. We compare them with level-2-based baselines that process sampled order-book snapshots and simple statistics instead of their underlying messages. Across three markets and four prediction horizons, our models achieve the highest mean macro-F1 in eleven of the twelve settings in a comparison against other benchmark models of varying sizes. Both our models achieve sub-millisecond median inference on a single Apple M2 CPU thread and have serialized state dictionaries below 70 kB. MBOFormer is 5.1x-8.1x faster than the million-parameter baselines at comparable predictive quality. Our results show that fine-grained market event history can reduce the need for model size under tight deployment constraints for short-term equity and electricity price forecasting tasks.

Complexity vs Empirical Score

  • Math Complexity: 5.0/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a novel approach to LOB forecasting using compact transformers on level-3 data, demonstrating strong empirical results across multiple markets. The methodology is clearly explained, and the focus on low-latency deployment is highly practical.

Research Flowchart

  flowchart TD
    A[Research Goal: Low-Latency LOB Forecasting] --> B(Methodology: Compact Causal Transformers);
    B --> C{Data: Level-3 Market Event History};
    C --> D[Models: MBOFormer & MBOFusion];
    D --> E(Computational Process: Train & Evaluate Models);
    E --> F{Key Outcomes: High F1, Low Latency, Small Size};