I am a Fellow in Management Studies at Exeter College and an Associate Professor of Operations Management at the Saïd Business School, Oxford.
Alongside my role at Oxford, I hold a visiting scholar position at the Harvard Kennedy School as a Harvard Data Science Initiative fellow. I received my Ph.D. in Operations Research from the Massachusetts Institute of Technology (MIT) and completed my undergraduate studies at the department of Management Science and Technology at the Athens University of Economics and Business.
My research vision is to combine my experience and rigorous training in operations research with my creativity to build analytical models that make a positive impact on society. To pursue this vision, my research agenda has primarily focused on developing new methods and models for healthcare and insurance practitioners using data-driven methodologies.
Specifically, I have developed new machine learning algorithms to address major data imperfections – such as missing values, censored observations, and unobserved counterfactuals – that are commonly found in real-world datasets. Leveraging a wide variety of data sources, including health and claims records, longitudinal studies, and unstructured medical reports, my research has resulted in predictive and prescriptive models that improve patient care and hospital operations in the context of cardiovascular and cerebrovascular diseases as well as COVID-19. My work highlights the importance of interpretability and the design of systems that facilitate engagement of the decision-maker and integration into healthcare organizations.
In parallel, to propel the adoption of these methodologies, I have introduced the area of algorithmic insurance, proposing a quantitative framework to estimate the litigation risk of machine learning models. My research focuses on the development of risk evaluation techniques that enable modern institutions to manage the risk exposure resulting from the implementation of analytical decision tools.
You can view Professor Orfanoudaki’s departmental web page here.