Lecturer in Credit Risk and Fin Tech
Roles and Responsibilities
Co-Organiser of the annual QFRA: Quantitative Finance and Risk Analysis international symposium (Zakynthos 2026, Corfu 2025, Santorini 2024, Crete 2023, Kos 2019, Mykonos 2018)
Research Director supervising PhD students in Artificial Intelligence, East Asian Economies, Statistics, and Econometrics;
Course Designer & Instructor: • Time Series Forecasting, CMSE11640 (Postgraduate) • Data-Driven Business Insights, CMSE11648 (Postgraduate) • Statistical Learning in Banking, CMSE11651 (Postgraduate)
Background
Stavros's research focuses on causal inference and forecasting in complex financial systems. His work bridges applied mathematics and quantitative investment practice, building methodologies that move from peer-reviewed publication into use by wealth managers, family offices, and portfolio managers.
Two methodologies anchor the work. Pattern Causality detects the hidden causal links that move markets and break portfolios; it is published in two papers in the Proceedings of the National Academy of Sciences (PNAS) with National Academy member Prof. H. Eugene Stanley (Boston University), and is available as open-source Python and R packages used by quantitative researchers and risk teams worldwide. AION is a geometric forecasting framework that captures the hidden attractor structure of complex systems; across 130+ benchmarks in eight scientific and financial domains it outperforms leading foundation models at near-zero compute cost (manuscript in preparation).
In parallel, Stavros is Managing Director of Pylos Consulting Ltd, building investment frameworks for family offices and wealth managers. He holds a PhD in Applied Mathematics from the University of Liverpool, where his thesis won Best PhD Thesis 2020, and was a Visiting Scholar at the California Institute of Technology.
Research Interests
Causal inference in complex financial systems. Pattern Causality is a methodology for detecting hidden causal links that move markets and break portfolios. Published in two papers in the Proceedings of the National Academy of Sciences (PNAS) with National Academy member Prof. H. Eugene Stanley (Boston University). Available as open-source Python and R packages, used by quantitative researchers and risk teams worldwide.
Geometric time-series forecasting. AION applies attractor geometry and Takens embedding to capture the hidden structure of complex systems. Across 130+ benchmarks in eight scientific and financial domains, AION outperforms the largest foundation models at near-zero compute cost. Manuscript in preparation.
Investment frameworks under regime uncertainty. Combining top-down macro regime analysis with concentrated single-name research; frameworks for investment decision-making across both liquid macro instruments and individual securities.