Machine Learning and Risk Evaluation – McLaren

In the machine learning field, statistical learning and clustering play a crucial role. Their application in our daily life is no longer to be proven. Besides, technological advances in recording have raised the challenge of managing functional data. For risk assessment, an actual challenge is to deal with extremal risks. The overall objective of the project is to bring significant innovations in the fields of statistical learning (and more particularly unsupervised learning, i.e. clustering) and risk assessment, linked by the problem of level sets estimation. To achieve this, the project has set three specific objectives: Objective 1 : Improve and propose quantization or depth based clustering methods for this new type of data (Machine Learning) ; Objective 2 : Address the topic of risk evaluation ; Objective 3 : Link these two axis by a transversal axis “level sets estimation”.