Detra Note 2022-1 | Insurance analytics with k-means and extensions13/01/2022
Lunch & Learn: “Features with flat partial dependence plots up to a certain level – not important?”03/02/2022
Lunch & Learn “Insurance Analytics: clustering techniques”
We are pleased to announce that our next Lunch & Learn will take place on Fev. 17, 2022 from 12:30 to 13:30
. Get your free access now!
It will be given in French
with material in English by our Scientific Director, Donatien Hainaut
, Ph.D. You follow this session online or onsite.
This Lunch and Learn proposes to discuss the results of our Detranote"Insurance analytics with k-means and extensions
The k-means algorithm and its variants are popular techniques of clustering. Their purpose is to uncover group structures in a dataset. In actuarial applications, these methods detect clusters of policies with similar features and allows to draw a map of dominant risks. This L&L starts with a review of the k-means algorithm and develops next two extensions to manage categorical features. We present a mini-batch version that keeps computation time under control when analysing a high-dimensional dataset. We next introduce the fuzzy k-means in which policies can belong to multiple clusters. Finally, we conclude by a detailed introduction to spectral clustering.