Skip to main content
Project

AI-LOB – Advanced AI Forecasting for Limit Order Books

Tampere University
Duration of project1.9.2025–28.2.2027
Area of focusTechnology

With AI-LOB, you stay a step ahead of other high-frequency traders.

In financial markets, market makers, hedge funds, proprietary trading firms, and asset managers can monetize accurate and reliable predictions of order flow for inventory management, directional trading, and optimal execution.

Traditional mathematical models are unable to predict order flow dynamics due to their complexity, especially as trading algorithms continuously react to each other’s actions. AI models, on the other hand, must be extremely fast to meet strict latency requirements.

Building on over 10 years of research on state-of-the-art ML models, we develop commercial machine learning solutions to address this challenge. On the research side, we have published in leading AI journals and are widely recognized, with our work among the most cited in the field. Examples include the TABL model (cited 300+ times) and recently developed LOBERT model (NeurIPS workshop best poster award)

Our models forecast LOB messages and features, generating real-time signals within short-term opportunity windows. The key advantages of our solution are speed, adaptability, and accuracy. The models can be integrated into clients’ existing in-house or commercial trading systems, directly translating into financial gains and improved profitability.

Given the highly international nature of financial markets, our business is globally scalable, with strong growth potential in major financial hubs where demand for advanced AI-driven trading solutions is high.

 

Contact persons

Prof. Juho Kanniainen, juho.kanniainen [at] tuni.fi (juho[dot]kanniainen[at]tuni[dot]fi)