用生成模型模拟市场微观结构，可零样本泛化到亚太市场。
TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure
- 构建524M参数的生成Transformer，直接从超10亿笔交易中学习跨资产通用表示。
- 生成序列能复现金融收益的重尾、波动聚集等典型特征，分布误差比基准低2-3倍。
- 无需资产定制化，适合用于合成数据、压力测试和基于学习的交易策略研究。
基础模型已通过大规模异构数据学习通用表征，革新了从语言到基因组的多个领域。我们提出TradeFM，一个524M参数的生成式Transformer，将此范式引入市场微观结构分析，直接从超过9,000只股票的数十亿笔交易事件中学习。为实现跨资产泛化，我们设计了尺度不变特征与统一的标记化方案，将多模态订单流事件序列映射为统一离散序列，消除了资产特异性校准需求。结合确定性市场模拟器，TradeFM生成的演进序列重现了金融收益的关键典型事实，包括重尾、波动聚集及回报无自相关性。定量上，其分布误差比Compound Hawkes基线降低2-3倍，并在零样本情况下泛化至地理上分布外的亚太市场，仅出现适度困惑度下降。结果表明，尺度不变的交易表征捕捉到了市场微观结构中的可迁移结构，为合成数据生成、压力测试及基于学习的交易代理提供了新路径。
原文摘要 · Abstract (English)
Foundation models have transformed domains from language to genomics by learning general-purpose representations from large-scale, heterogeneous data. We introduce TradeFM, a 524M-parameter generative Transformer that brings this paradigm to market microstructure, learning directly from billions of trade events across >9K equities. To enable cross-asset generalization, we develop scale-invariant features and a universal tokenization scheme that map the heterogeneous, multi-modal event stream of order flow into a unified discrete sequence -- eliminating asset-specific calibration. Integrated with a deterministic market simulator, TradeFM-generated rollouts reproduce key stylized facts of financial returns, including heavy tails, volatility clustering, and absence of return autocorrelation. Quantitatively, TradeFM achieves 2-3x lower distributional error than Compound Hawkes baselines and generalizes zero-shot to geographically out-of-distribution APAC markets with moderate perplexity degradation. Together, these results suggest that scale-invariant trade representations capture transferable structure in market microstructure, opening a path toward synthetic data generation, stress testing, and learning-based trading agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。