BMLL and Simudyne partner on AI market simulation
BMLL has partnered with Simudyne, a generative AI and agent-based market simulation platform; BMLL’s harmonised historical Level 2 and Level 3 order book data will serve as the training and execution data for Simudyne’s Pulse simulator. The companies say the combination will let market participants run reactive market simulations, perform market replays and test system performance.
According to the release, Simudyne has begun pre-training generative AI “Large Market Models” of intraday order flow on granular market data, alongside its existing rule-based agent-based modelling. The resulting simulator offers what the companies call “reactive” back-testing; the simulated market responds to a user’s executed orders in real time rather than replaying static history.
The companies list use cases across algo traders and quants, execution and TCA analysts, trading technology teams, exchanges, and risk and clearing teams. These include estimating slippage and market impact before execution, connecting staging systems to the simulated exchange via FIX or APIs, testing matching engine logic and circuit breakers, and stress-testing margin and default-fund models.
The partnership is enabled by Simudyne’s participation in the BMLL Activate Data Credits Programme, which offers selected partners lower to no upfront data licence costs during the build phase, according to BMLL.
Paul Humphrey, Chief Executive Officer of BMLL, said: “High-quality training data is the single most critical ingredient for sophisticated, AI-driven financial modelling. By hosting Simudyne’s simulation models directly within the BMLL Data Lab, we will be able to give our clients a safe, highly realistic sandbox to run reactive simulations on top of our definitive historical order book.”
Justin Lyon, Chief Executive Officer of Simudyne, said: “As we move towards data-driven, generative AI models, simulation fidelity is only as strong as the data underpinning them.”
BMLL was acquired by Nordic Capital in October 2025.
