BMLL and Simudyne partner to advance AI-driven market

By Divya Shah

BMLL, a provider of harmonised historical market data and analytics, has partnered with Simudyne, a specialist in generative AI and agent-based simulation, to develop advanced market simulation capabilities for capital markets participants. 

The collaboration combines BMLL’s Level 2 and Level 3 historical order book datasets with Simudyne’s Pulse simulator, enabling users to conduct realistic market simulations, replay trading sessions and test system performance in dynamic market environments. 

Under the partnership, Simudyne has begun training its generative AI-based “Large Market Models” using BMLL’s granular market data. The models are designed to generate synthetic tick data and support client-specific fine-tuning, complementing Simudyne’s existing rule-based agent modelling framework. 

Paul Humphrey, Chief Executive Officer of BMLL, said, “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. Ultimately, this collaboration serves as a powerful proof-of-concept, establishing BMLL data as the premier foundation for firms to train their own AI models, while reinforcing our ongoing commitment to driving the next wave of innovation across global capital markets.” 

The companies said the resulting simulator moves beyond traditional historical replay by introducing reactive back-testing capabilities, allowing simulated markets to respond in real time to users’ trading activity. 

The integrated platform is expected to support a range of use cases across the capital markets ecosystem. Algorithmic traders and quantitative teams can test and optimise execution strategies, while transaction cost analysis (TCA) teams can evaluate market impact and trading costs before executing large orders. Trading technology teams can also use the environment to validate trading systems, latency performance and connectivity under realistic market conditions. 

Exchanges may leverage the simulation platform to assess changes to matching engines, trading protocols and order types before implementation, while risk and clearing teams can conduct stress testing and liquidity risk analysis across different market scenarios. 

Justin Lyon, Chief Executive Officer of Simudyne, said, “We are very excited to collaborate with BMLL to push the boundaries of market simulation. As we move towards data-driven, generative AI models, simulation fidelity is only as strong as the data underpinning them.” 

He added, “BMLL’s granular, high-resolution historical market data gives our models the depth needed to learn and reproduce real market dynamics at the order-book level. Together, we are creating the next generation of market simulation environment that bridges historical market behaviour and realistic synthetic markets.” 

The partnership is supported through Simudyne’s participation in the BMLL Activate Data Credits Programme, which provides selected partners with structured access to BMLL’s historical market datasets, Data Lab and Data Feed. The programme is designed to accelerate the development, testing and commercialisation of analytics and data-driven solutions while reducing upfront data licensing costs.