Our research portfolio is driven by real-world challenges that stand to benefit from machine learning and related approaches. Our goal is to spark interdisciplinary work, with application domains that are dictated by the need for support. Colleagues from the University of Edinburgh are always welcome to reach out to the lab director to explore cases for advice or collaborative projects.

Past and current work related to the lab ranges from financial markets, data privacy and policing to public health and the physical sciences. As such, our research interests are broad and focus on where suitable methodology has the potential to solve new and interesting problems.

Selected outputs

• Caceres and Moews (2024), “Evaluating utility in synthetic banking microdata applications”, working paper
• Ibikunle et al. (2024), “Can machine learning unlock new insights into high-frequency trading?”, working paper
• Moews (2024), “On random number generators and practical market efficiency”, Journal of the Operational Research Society 75(5):907-920
• Dai et al. (2024), “Physics-informed neural networks in the recreation of hydrodynamic simulations from dark matter”, Monthly Notices of the Royal Astronomical Society 527(2):3381-3394
• Moews and Gieschen (2023), “SCADDA: Spatio-temporal cluster analysis with density-based distance augmentation and its application to fire carbon emissions”, working paper
• Gieschen et al. (2023), “SynthEco - A multi-layered digital ecosystem for analysing complex human behaviour in context”, International Journal of Population Data Science 8(3):19

For a complete list of research outputs, please follow the links to the profiles on the Members page.