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

By Maxime Kawawa-Beaudan, Srijan Sood, Kassiani Papasotiriou, Daniel Borrajo, Manuela Veloso

Published 2026-02-27

Everscope rating
1804.3
Relevance to quantitative trading
9 / 10
Implementation complexity
8 / 10
Reproducibility
3 / 5

About this paper

Methodology: TradeFM. Problem types: Generative Modeling, Sequence-to-Sequence Learning, Zero-shot Learning, Transfer Learning, Density Estimation, Time Series Forecasting, Reinforcement Learning, Anomaly Detection, Risk Management.

arXiv:2602.23784 ยท Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.