Clustering algorithms aim to uncover hidden structure in data sets. Objects are grouped in such a way that the created groups are as much as possible heterogeneous between each-others.
The aim of this session is to cover unsupervised learning techniques for visualizing and analyzing a dataset. This course focuses on actuarial applications of clustering methods. By adapting these algorithms to manage categorical features, we can detect dominant sub-populations of policies. The analysis of their claims allows a posteriori to draw a synthetic map of insured risks.
The course is illustrated with examples in Python provided to participants.
Principal components in a nutshell.
Treatment of categorical variables with a chi-square distance.
Factorial components analysis of categorical datasets.
K-means, K-means++, batch K-means for categorical datasets
Fuzzy clustering.
Graph representation of data and spectral clustering.
Scientific Advisor, Detralytics
Professor, UCLouvain
Date : On-Demand
Duration : 3h
Accreditation : 3CPD | 18PPC
Level : All
At the end of the training, participants will be able to:
Donatien Hainaut is a Scientific Advisor at Detralytics and a professor at UCLouvain (Belgium), where he serves as the Director of the Master’s program in Data Science with a statistical orientation. Prior to this, he held several academic positions, including Associate Professor at Rennes School of Business and ENSAE in Paris. He also has extensive industry experience, having worked as a Risk Officer, Quantitative Analyst, and ALM Officer.
Donatien is a Qualified Actuary and holds a PhD in the field of Asset and Liability Management. His current research focuses on contagion mechanisms in stochastic processes and the applications of neural networks in insurance.
