# TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure

arXiv: https://arxiv.org/abs/2602.23784 · HTML: https://mlsanity.com/paper/2602.23784/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [Universal features of price formation in financial markets: perspectives from Deep Learning](https://mlsanity.com/paper/1803.06917/) (2018)
- [Get Real: Realism Metrics for Robust Limit Order Book Market Simulations](https://mlsanity.com/paper/1912.04941/) (2019)
- [The Impact of Depth on Compositional Generalization in Transformer Language Models](https://mlsanity.com/paper/2310.19956/) (2023)
- [MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model](https://mlsanity.com/paper/2409.07486/) (2024)
- [Synthetic Data Applications in Finance](https://mlsanity.com/paper/2401.00081/) (2023)
- [Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network](https://mlsanity.com/paper/2309.00638/) (2023)
- [Limit Order Book Dynamics and Order Size Modelling Using Compound Hawkes Process](https://mlsanity.com/paper/2312.08927/) (2023)
- [ABIDES-Economist: Agent-Based Simulator of Economic Systems with Learning Agents](https://mlsanity.com/paper/2402.09563/) (2024)
- [Scalable Representation Learning for Multimodal Tabular Transactions](https://mlsanity.com/paper/2410.07851/) (2024)
- [LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data](https://mlsanity.com/paper/2502.09172/) (2025)
- [TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data](https://mlsanity.com/paper/2502.15757/) (2025)
- [Ensemble Methods for Sequence Classification with Hidden Markov Models](https://mlsanity.com/paper/2409.07619/) (2024)

## Built on by (most cited first, 6 of 6)

- [Scaling Laws for Behavioral Foundation Models over User Event Sequences](https://mlsanity.com/paper/2606.05257/) (2026)
- [LOB-ID: Evaluating Synthetic Market Data by Inception Distances](https://mlsanity.com/paper/2608.13082/) (2026)
- [FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching](https://mlsanity.com/paper/2608.13096/) (2026)
- [M3: A State-Event Generative Foundation Model for Market Microstructure Dynamics](https://mlsanity.com/paper/2608.19227/) (2026)
- [ReLOBGen: Replayable Limit Order Book Message Generation](https://mlsanity.com/paper/2609.35867/) (2026)
- [Market Impact Estimation via Causal Foundation Models](https://mlsanity.com/paper/2610.12537/) (2026)

## Abstract (arXiv)

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.