Overview
Turning data into decisions
This research area develops and applies statistical, computational, and mathematical methods to address complex decision problems in business and information systems. We bridge the gap between abstract quantitative theory and practical managerial application.
Our work spans structural equation modelling, machine learning, multi-criteria decision analysis, and simulation, providing the methodological backbone for empirical research across all ISeB Lab research areas.
Methodological rigour
Advancing best practices in survey design, measurement, and causal inference for IS research.
Applied decision systems
Building tools that translate analytical outputs into actionable recommendations for managers.
Cross-disciplinary reach
Methods developed here underpin research in entrepreneurship, marketing, operations, and more.
Image placeholder
What we study
Core Research Themes
Six methodological and applied themes at the intersection of quantitative analysis and business decision-making.
Structural Equation Modelling & Survey Methods
We develop and refine methods for theory testing in information systems and management research, with a focus on PLS-SEM, CB-SEM, and mixed-methods designs. Research addresses measurement validity, common method bias, and the appropriate use of variance-based versus covariance-based approaches.
- PLS-SEM and CB-SEM: model specification and evaluation
- Scale development and construct validity assessment
- Common method bias detection and remediation
- Longitudinal and multi-group comparative designs
Decision Support Systems
We design and evaluate information systems that assist managers in making structured and semi-structured decisions. Research covers system architecture, interface design, user acceptance, and the integration of AI and analytics engines into practical decision workflows.
- DSS architecture: data, model, and dialogue components
- Group decision support systems and collaborative tools
- AI-augmented decision-making and explainability
- Evaluation frameworks for DSS effectiveness
Multi-Criteria Decision Analysis
We apply and extend MCDA methods — AHP, TOPSIS, VIKOR, ELECTRE — to complex organisational decisions involving multiple conflicting criteria. Applications span supplier evaluation, technology selection, strategic investment, and public policy assessment.
- AHP and ANP for priority weighting under uncertainty
- Fuzzy MCDA methods for ill-defined criteria
- Hybrid MCDM frameworks combining multiple methods
- Applications in IS project selection and IT governance
Data Analytics & Business Intelligence
We investigate how organisations collect, process, and derive value from large and complex datasets. Research addresses the technical architectures of BI platforms, the human factors of data-driven culture, and the ethical dimensions of algorithmic decision-making.
- Business intelligence adoption and organisational impact
- Text mining and natural language processing in IS research
- Social network analysis for IS and management studies
- Data governance, quality, and stewardship
Machine Learning in Business Applications
We develop and evaluate machine learning models for business prediction and classification tasks, and study the organisational conditions under which ML adoption creates value. Research bridges the technical and managerial aspects of deploying AI in business contexts.
- Predictive modelling for customer churn and lifetime value
- Ensemble methods and model interpretability
- ML adoption barriers and success factors in SMEs
- Responsible AI: fairness, accountability, and transparency
Simulation & Optimisation
We use discrete-event simulation, agent-based modelling, and mathematical optimisation to model complex systems and identify optimal policies. Applications include healthcare capacity planning, supply chain network design, and digital platform resource allocation.
- Discrete-event simulation for process and capacity analysis
- Agent-based modelling of market and social systems
- Mathematical programming for resource allocation problems
- Metaheuristics: genetic algorithms, simulated annealing
People
Researchers in this area
Maria Balafouti
Undergraduate Student Business & Data Analytics, Stem Education
Vangelis Rizoudis
Student E-Government, Business & Data Analytics, Project ManagementNeed analytical support for your research?
We offer methodological expertise and decision modelling support for collaborative research projects. Reach out to discuss how we can contribute to your work.