Statistics and data analytics

The Statistics and Data Analytics Research Group brings together researchers working at the intersection of statistics, data science, mathematical modelling, and applied analytics. Our research is driven by the development of rigorous statistical methods and data-driven approaches to address complex and emerging challenges across finance, sustainability, climate, healthcare, and other domains.

We develop and apply statistical models, computational methods, and data analytics techniques to extract meaningful insights from complex and often high-dimensional data.

Our work aims not only to advance statistical methodology but also to translate these advances into practical solutions for real-world problems, supporting better decision-making, risk assessment, forecasting, and policy development.

Research themes

Our research spans a broad range of methodological and application-driven areas, including but not limited to:

Finance and quantitative risk management

We develop statistical and data-driven methods for understanding, measuring, and managing financial risks in increasingly complex and uncertain environments. Areas of interest include financial modelling and forecasting, quantitative risk management, uncertainty quantification, time-series analysis, volatility modelling, extreme-value analysis, portfolio and market risk, and stress testing.

Our research also considers emerging challenges arising from interconnected financial, economic, environmental, and geopolitical risks, with the aim of developing robust tools for risk-informed decision-making.

Decarbonisation and sustainable development

Statistical modelling and data analytics play an important role in understanding and supporting the transition towards a low-carbon and sustainable economy. Our research explores quantitative approaches to measuring, modelling, and forecasting emissions and energy-related outcomes, as well as evaluating the effectiveness of decarbonisation strategies.

Potential areas include carbon emissions modelling, energy analytics, sustainable finance, transition risk, climate-related decision-making, and data-driven approaches to net-zero pathways.

Emerging and systemic risks

Modern societies face increasingly interconnected and uncertain risks, including climate change, extreme weather events, environmental hazards, and other emerging risks. We develop statistical and computational approaches for modelling uncertainty, assessing rare and extreme events, and understanding the potential impacts of these risks.

Research in this area may involve extreme-value statistics, spatial and spatio-temporal modelling, risk forecasting, uncertainty quantification, resilience analysis, and scenario-based risk assessment. A particular interest is placed on developing methods that can support organisations, policymakers, and communities in anticipating and managing risks in a changing environment.

Diseases and healthcare analytics

The group applies statistical modelling and data analytics to challenges in healthcare, epidemiology, and disease research. We are interested in developing methods for analysing complex health data, identifying patterns and risk factors, improving prediction, and supporting evidence-based healthcare decisions.

Research may include disease modelling and prediction, epidemiological statistics, survival analysis, longitudinal data analysis, health risk assessment, healthcare analytics, and statistical learning for medical and public-health applications.

Cross-disciplinary and collaborative research

Many of the challenges addressed by the group are inherently interdisciplinary. We therefore actively encourage cross-disciplinary collaboration and welcome opportunities to work with researchers across different academic fields.

The group invites collaboration with researchers and research teams across Heriot-Watt University, including colleagues from other Schools and campuses, as well as with researchers at universities, research institutions, government organisations, and industry partners across the UAE and the wider region.

We are particularly interested in collaborations that combine statistical and data-analytic expertise with domain knowledge to address important real-world problems. Potential collaborations may include joint research projects, grant applications, consultancy and knowledge-exchange activities, postgraduate supervision, workshops, and interdisciplinary research initiatives.

Current projects

Forecasting respiratory illness outbreaks and insurance costs

This project will develop a UAE-focused machine learning system to detect respiratory disease outbreaks early and forecast their impact on healthcare and insurance costs. By combining insurance claims with weather, air quality, mobility and behavioural data, the system will aim to predict surges in respiratory-related claims at least two weeks in advance.

The project will identify the key environmental and behavioural factors driving respiratory illness and assess the effectiveness of preventive measures such as mask mandates and public health campaigns. The findings will support health authorities, policymakers and insurance company in improving cost forecasting, reserve planning and public health responses.

Through collaboration between UNSW Sydney, Heriot-Watt University Dubai and ADNIC, the project will strengthen Australia-UAE research partnerships and build capacity in health analytics, while sharing findings with industry, policymakers and the wider community.

Researchers

Dr. Katja Ignatieva, School of Risk and Actuarial Studies, The University of New South Wales (UNSW) Australia; Dr. Haslifah Hasim, Heriot-Watt University Dubai; Muhammad Zafar, Abu Dhabi National Insurance Company.

Funding

2025-26 Council for Australian Arab Relations (CAAR) Grant.