Agni Orfanoudaki

Agni Orfanoudaki

Associate Professor of Operations Management


Saïd Business School
University of Oxford
Park End Street
Oxford
OX1 1HP

Profile

Alongside her role at the School, Agni is a Fellow in Management Studies at Exeter College and a visiting scholar at the Harvard Kennedy School as a Harvard Data Science Initiative fellow. 

Agni’s research agenda has primarily focused on developing new methods and models for healthcare practitioners using data-driven techniques. She is also studying the implications of these models on automated decision making, setting the foundations in the novel field of algorithmic insurance.

Prior to joining Oxford, Agni received a PhD in Operations Research from the Massachusetts Institute of Technology (MIT). She gained industry experience working at McKinsey & Company and holds a BSc in Management Science and Technology from the Athens University of Economics and Business, Greece.

Expertise:

  • Business analytics
  • Digital operations
  • Healthcare operations
  • Algorithmic insurance
  • Personalised medicine

Research

Agni’s research interests lie at the intersection of machine learning and optimisation, with applications to healthcare and insurance.

She has developed new algorithms to address major data imperfections that are commonly found in real-world datasets, like missing values, censored observations, and unobserved counterfactuals. Leveraging a wide variety of data sources, including health and claims records, longitudinal studies, and unstructured medical reports, her 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. Her work highlights the importance of interpretability and the design of systems that facilitate engagement of the decision-maker and integration into healthcare organisations.

In parallel, to propel the adoption of these methodologies, she has introduced the area of algorithmic insurance, proposing a quantitative framework to estimate the litigation risk of machine learning models. Her research focuses on the development of risk evaluation techniques that will enable modern institutions to manage the risk exposure resulting from the implementation of analytical decision tools.

Data Driven Decisions Lab (3DL)

Agni leads on the development of the Data Driven Decision Lab (3DL) research project which aims to address the challenge of how machine learning models impact real-world decision making. The group conducts theoretical and empirical research in the field, while working with industry, academic, and practitioner partners within sectors ranging from healthcare to revenue management.

Engagement

Agni’s work involves creating practical solutions based on state-of-the-art analytics techniques.

Her work addresses real-world industry needs drawn from conversations with and requests from decision-makers in health and insurance organisations. She has collaborated with numerous institutions, including a major medical society, an international reinsurance company, and more than eight hospitals from the US and Europe.

Teaching

Agni leverages her experience and research in digital operations and artificial intelligence to deliver courses at the School.

She teaches the core Technology and Operations Management courses for the MBA, Executive MBA, and undergraduate programmes. She is also a Fellow in Management Studies at Exeter College and leads the elective class on Machine Learning for Business. 

At MIT she was part of the teaching team for the Operations Management and Business Analytics courses on the MBA and Executive MBA programmes of the Sloan School of Management. Agni also served as a mentor and instructor for graduate courses at the Master of Business Analytics and at the department of Electrical Engineering and Computer Science. She is the co-instructor and class designer of an executive class for healthcare professionals delivered at Hartford HealthCare, Connecticut’s most comprehensive healthcare network.