Dr Alma Rahat is a Reader in Data Science & Decision Intelligence at Loughborough University. His research focuses on evolutionary and Bayesian optimisation, particularly on developing acquisition functions for single‑ and multi‑objective problems and on identifying feasible solution spaces in computationally expensive settings. He has a strong record of industrial and interdisciplinary collaboration, contributing to applications in engineering design, healthcare, education, and public policy. His work appears in leading journals and conferences and has received several distinctions, including the Best Paper Award in the Real‑World Applications track at GECCO (2014), the David B. Martin Best Paper Award (2025), and a patent with Hydro International Ltd.
He played a pivotal role in the Welsh Government’s COVID‑19 response, leading parameter optimisation for the Swansea COVID‑19 model – the only medium‑term projection tool in Wales – which informed weekly briefings to the First Minister and the UK Health Security Agency. This work was supported by major funding from the Welsh Government (Co‑PI) and EPSRC (PI).
Dr Rahat is an active contributor to the optimisation community, serving as a member of the IEEE CIS Task Force on Data‑Driven Evolutionary Optimisation of Expensive Problems, leading the Surrogate‑Assisted Evolutionary Optimisation (SAEOpt) workshop at GECCO since 2016, and acting as Proceedings Chair for GECCO 2022. He also led Swansea University’s entry into the Turing University Network, later serving as Turing Academic Liaison, and was a Turing Fellow from 2024 to 2026.
He holds a BEng (Hons) in Electronic Engineering from the University of Southampton, a PhD in Computer Science from the University of Exeter, a PgCert in Teaching in Higher Education from Swansea University, and is a Fellow of the Higher Education Academy (FHEA). He has previously held academic posts at Exeter, Plymouth, and Swansea.
Dr Rahat’s research focuses on evolutionary and Bayesian optimisation, with core contributions in:
- Acquisition functions for single‑ and multi‑objective optimisation
- Constrained optimisation, including methods for identifying and exploring feasible solution spaces
- Active learning and surrogate‑assisted modelling for computationally expensive simulations
- Integrating optimisation with simulation, uncertainty quantification, and decision intelligence
His work has delivered impact across several applied domains, including:
- Public health modelling, where he led optimisation for the Swansea COVID‑19 model used by the Welsh Government
- Engineering design, with projects in hydrodynamics, structural design, and environmental and coastal modelling
- Educational technology, including Bayesian comparative judgement and research on human–AI interaction
- Human‑centred AI, supporting decision‑making in clinical, industrial, and policy contexts
His research has been supported by major funders such as EPSRC, the Welsh Government, the Leverhulme Trust, and multiple industry partners.