An introduction to robust and efficient statistical learning algorithms with applications in actuarial science

The big data era represents an opportunity for statistical methods to shine, through applications relevant to a wide spectrum of fields, including actuarial science. In order to seize and make the most out of this opportunity, researchers and practitioners must, however, effectively manage the challenges that big data pose. The intern will be exposed to two challenges: data quality (taking the more specific form of data bases containing outliers because of data with gross errors or extreme values) and scalability of the numerical methods required for inference. The intern will be introduced to novel Bayesian robust methods and Markov chain Monte Carlo algorithms to address these issues. The intern will explore the benefits of applying these methods and algorithms in actuarial contexts, in particular in the field of general insurance. This last part will represent a contribution and may lead to a paper in an actuarial journal.

Faculty Supervisor:

Philippe Gagnon

Student:

Partner:

University of Oxford

Discipline:

Mathematics

Sector:

Finance and Insurance

University:

Université de Montréal

Program: