TradeFM: 一种用于交易流和市场微观结构的生成基础模型
TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure
AI总结：
TradeFM是一种基于生成Transformer的市场微观结构基础模型，通过学习大规模交易数据实现跨资产泛化，有效捕捉市场特征并提升合成数据生成与交易策略研究能力。
摘要：
基础模型通过从大规模异质数据中学习通用表示，已将领域从语言扩展到基因组。我们介绍了TradeFM，一种具有5.24亿参数的生成Transformer，将这一范式应用于市场微观结构，直接从数以十亿计的交易事件中学习，涵盖超过9000只股票。为实现跨资产泛化，我们开发了尺度不变特征和一种通用的标记化方案，将订单流的异质、多模式事件流映射到统一的离散序列中，消除了资产特定的校准。与确定性市场模拟器集成后，TradeFM生成的回放能够再现金融回报的关键 stylized facts，包括厚尾、波动率聚集和收益自相关缺失。定量上，TradeFM的分布误差比Compound Hawkes基线低2-3倍，并能泛化到地理上分布外的亚太市场，仅经历适度的困惑度下降。这些结果表明，尺度不变的交易表示捕捉了市场微观结构中的可转移结构，为合成数据生成、压力测试和基于学习的交易代理开辟了道路。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
