Skip to navigation | Skip to main content | Skip to footer

Research themes

The Centre has structured its research activity around four key themes which are central to the study of decision sciences today.

The Decision Analytics and Behaviour theme promotes the research, development, application and dissemination of novel theories and methods for supporting and improving decision making.

Our research focuses on multiple criteria decision analysis (MCDA), multiple objective optimisation, decision support systems, decision makers’ preference analysis and modelling, decision behaviour and descriptive research, and group decision making and decision making processes.

The main thrust of our research seeks to help decision-makers and policymakers tackle complex decisions with multiple stakeholders, in the face of uncertainty, and we have an impressive showcase of completed projects in diverse sectors such as manufacturing, transportation, telecoms, engineering and healthcare.

Our work has been funded by multiple funders including EPSRC, ESRC, UKRI, and the EU (Horizon 2020 Programme), and more recently by the UK Technology Strategy Board, the Alan Turing Institute and Innovate UK, as well as industry.

Theme Lead: Nadia Papamichail
Theme members: Yu-Wang Chen, Oscar De Bruijn, Manuel Lopez-Ibanez, Dong-Ling Xu, Jian-Bo Yang, Xiao-Jun Zeng

The Centre has a track record of research in the area of data analytics and its applications. We have specific expertise in the areas of probabilistic inference and multi-criteria approaches to data analysis.  Novel tools developed in our centre include the Evidential Reasoning (ER) Approach, the Belief-Rule-Base (BRB) Approach, and the multi-objective clustering method MOCK.

Academics within the theme develop customised approaches suitable for applications ranging from Finance, Operations, Product Development and Marketing to Bioengineering and Healthcare. Typically, these applications involve the integration of complex (and often big) data sources, the use of explorative and network analysis methods to obtain insight into the structure and relationships in the data, and / or the development of predictive models that can support particular business needs.

Theme Lead: Dong-Ling Xu
Theme Members: Richard Allmendinger, Jian-Bo Yang, Dong-Ling Xu, Swati Sachan, Xiajun Zeng, John Keane, Mario Garza-Fabre, Luis Ospina-Forero, Yu-wang Chen

The Centre has extensive experience in the area of modelling, simulation and optimisation, and the application of these concepts to real-world problems. We have specific expertise in the areas of heuristics, evolutionary computation, automatic configuration of optimisation algorithms, multi-objective optimisation, multi-criteria decision-making, and optimisation subject to expensive evaluations and uncertainty. Most of our work is interdisciplinary and often in collaboration with industrial partners.

Academics within the theme develop and apply novel optimisation techniques to a variety of problems, for example in healthcare, manufacturing, software and product design, marketing, and portfolio optimisation. Furthermore, our academics contribute to the design of mathematical models (e.g. a manufacturing process or behaviour of decision-makers) and the translation of these models into a (computational) simulator or an experimental platform, which then interacts with an optimisation algorithm.

Theme Lead: Richard Allmendinger
Theme Members: Richard Allmendinger, Manuel Lopez-Ibanez, Ludmil Mikhailov, Jian-bo Yang

The Centre has established research strengths in the areas of artificial intelligence and knowledge-based systems. Specific work involves intelligent fraud prevention, predictive analytics, customer analytics, metaheuristics, belief rule-based systems and intelligent decision support systems (IDSS).

For example, academics are currently working with the Forensic Testing Service to develop an automated data analytics tool that analyses all available information and then makes informative and explainable recommendations for drug and alcohol testing cases.

Our research on IDSS focuses primarily on theoretical methods for multiple-criteria decision-making and applications of intelligent technologies, such as expert systems, evidential reasoning, fuzzy logic, belief rule-based models and genetic algorithms.

A software tool, called Intelligent Decision System (IDS) has been developed for solving many decision problems, such as clinical decision support, engineering system fault diagnosis, portfolio optimisation, performance modelling and impact assessment of sustainable energy systems. It is used by practitioners, decision analysts and researchers from more than 50 countries including organisations such as General Motors Company, the Belgian Nuclear Research Centre, and the Hong Kong Productivity Council.

Theme Lead: Yu-Wang Chen
Theme members: Yu-Wang Chen, Jian-Bo Yang, Dong-Ling Xu, Swati Sachan, Nadia Papamichail