发表机构
ETH Zurich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出紧凑Transformer模型MBOFormer和MBOFusion，利用三级订单簿事件历史在低延迟下实现高精度价格趋势预测，在多数市场设置中超越大模型基线，推理速度提升5倍以上。
AI 中文摘要
在股票和日内电力市场中，从限价订单簿进行短期价格趋势预测需要模型兼具预测质量、低单样本延迟和小序列化模型大小，以跟上快速且持续的市场更新。我们引入了MBOFormer，一个拥有7,203个参数的因果Transformer，以及MBOFusion，一个拥有14,371个参数的扩展版本，并带有慢时间上下文分支。这两个模型都处理逐市场订单（三级）级别的单个订单提交、取消和执行的完整历史。我们将它们与基于二级的基线进行比较，这些基线处理采样的订单簿快照和简单统计信息，而非底层消息。在三个市场和四个预测时间跨度上，在与各种规模的其他基准模型的比较中，我们的模型在十二个设置中的十一个中取得了最高的平均宏F1分数。我们的两个模型在单个Apple M2 CPU线程上实现了亚毫秒级的中位推理时间，序列化状态字典小于70 kB。在相当的预测质量下，MBOFormer比百万参数基线快5.1倍至8.1倍。我们的结果表明，在短期股票和电力价格预测任务的严格部署约束下，细粒度的市场事件历史可以减少对模型规模的需求。
英文摘要
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.
Comments*Equal contribution
