Head of Team (Computing), QA Higher Education (Ulster University)
Advancing intelligent systems. Developing people. Turning research into impact.
I'm a Computer Science academic, machine-learning researcher, and AI leader working at the intersection of adaptive intelligence, financial technology, education, and responsible innovation.
Where the work meets
Academic leadership, machine-learning research, industrial AI, and mentorship aren't separate tracks — each one feeds the others.
Teaching, curriculum development, academic quality, and leading a computing teaching team.
Adaptive ML, concept drift, fraud detection, biometric security, responsible AI.
Production systems in fintech, identity verification, AML, and MLOps.
Supporting students and early-career professionals moving into data and AI careers.
Featured Research
Adaptive machine learning, financial fraud detection, biometric security, and AI for health.
Okunola Orogun, L. Ogungbe, N. Adegboye, T. Adetuyi, S. Alabi
International Journal of Research in Engineering and Science (IJRES)
Examines machine-learning and behavioural-analysis strategies for detecting synthetic identity fraud and strengthening the security of financial ecosystems.
S.A. Oluwadare, I.P. Adegun, Okunola Orogun
International Journal of Research in Engineering and Science (IJRES)
Presents an ensemble deep-learning model that integrates multiple epidemiological data sources to predict Lassa fever outbreaks, developed under a TETFund National Research Fund grant.
Okunola Orogun, L. Ogungbe, A. Ajani, N. Adegboye, O. Ogunsola
European Journal of Contemporary Education and E-Learning
Explores strategies for deploying AI sustainably and equitably within UK higher education, connecting responsible-AI principles to educational-equity outcomes.
Okunola A. Orogun, Oluwaseun S. Adebayo, T.A. Favour-Bethy, O. Otasowie
International Journal of Computer Science and Mobile Computing
Proposes an adaptive accuracy-weighted ensemble approach for credit card fraud detection that responds to concept drift in transaction patterns, improving resilience over static ensemble baselines.
Research to Impact
Financial fraud patterns shift constantly — a model trained on last year's data quietly degrades against this year's attacks.
Doctoral and postdoctoral research into hybrid ensemble methods that detect and adapt to concept drift in real time.
Deployed as a real-time AML transaction-monitoring system and a patent-pending multi-modal biometric verification framework at Prembly Inc.
Measurable reductions in financial-crime exposure and identity-fraud risk across live client platforms, now informing teaching content on responsible AI deployment.
Latest Writing
Notes on adaptive ML, teaching, and moving research into production.
How doctoral research on adaptive credit-card fraud detection became a real-time anti-money-laundering system running against live transactions.
Read articleActive-learning pedagogy, industry case studies, and the case for keeping the feedback loop between code and explanation as short as possible.
Read articleA fraud model that scored 95% accuracy at launch can be quietly failing six months later — here's why, and what adaptive detection does about it.
Read articleMentorship
I mentor the way I teach: start from where someone actually is, connect every skill to a real problem, and give feedback that's honest enough to be useful. My own path went through a state scholarship, three degrees on two continents, and a career that moves between the lecture theatre and production AI systems — so I mentor people who are navigating similarly non-linear routes into data, AI, and research.
Explore MentoringOpen to research collaboration, speaking invitations, academic partnerships, AI consulting, and mentoring enquiries.