Industry-facing applications • Real-world impact • Cutting-edge machine learning
My research portfolio encompasses industry-facing AI applications addressing real-world challenges in financial services, healthcare, and maritime operations. These projects combine state-of-the-art machine learning techniques with domain-specific knowledge, delivering actionable insights for industry partners and policy makers.
Developed Tab-AML, a novel Transformer-based architecture for transaction monitoring in financial crime detection. This deep learning system processes sequential transaction data to identify suspicious patterns indicative of money laundering activities, achieving superior performance over traditional rule-based systems.
Leading a PhD project (funded studentship) in partnership with Hampshire and Isle of Wight Constabulary to develop digital health interventions for managing physical and mental well-being of blue light emergency responders. The project employs machine learning for predictive health analytics and personalised intervention design.
Supervising a PhD studentship with Clearwater Dynamics focused on predictive analytics for enhanced vessel operational efficiency. The project applies machine learning to maritime sensor data, fuel consumption patterns, and environmental variables to optimise routing, maintenance scheduling, and overall fleet performance.
Co-leading a £250,000 UKVI Knowledge Transfer Partnership between Bournemouth University and Nourish Care Limited, deploying AI and data science solutions to improve care delivery, operational efficiency, and resident outcomes in the UK health and social care sector.
Applied novel dynamic Autoregressive Distributed Lag (ARDL) machine learning models to simulate the impact of ICT infrastructure on patent intensity and innovation capacity in South Africa. This work demonstrates the application of advanced econometric techniques to evidence-based policy design for technology-driven economic development.
Developing a conceptual framework and strategic research agenda for human-centred AI design in financial technology applications. This work addresses ethical considerations, explainability requirements, and user trust in AI-driven financial services, with implications for regulatory compliance and responsible AI deployment.
I actively seek partnerships with industry, government agencies, and research institutions. My projects demonstrate a track record of securing competitive funding and delivering practical impact. I am currently accepting PhD enquiries in machine learning, FinTech AI, digital health, maritime analytics, and applied data science. Prospective students with strong quantitative backgrounds (computer science, mathematics, economics, engineering) are encouraged to make contact.