TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure
This work applies foundation models to market microstructure, potentially enabling synthetic data generation and learning-based trading agents.
The authors tackled the problem of modeling market microstructure by introducing TradeFM, a 524M-parameter generative Transformer trained on billions of trade events across over 9,000 equities, which achieves 2-3x lower distributional error than baselines and generalizes zero-shot to APAC markets with moderate perplexity degradation.
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.