Calendrier des événements

Partager sur :

Sparse Weighted K-means for groups of mixed-type variables

The Working Group on Risk - CREAR, with the support of the IDS dpt, Institut des Actuaires, LabEx MME-DII and the group BFA-SFdS, has the pleasure to invite you to the seminar by:

Prof. Madalina OLTEANU, Université Paris Dauphine PSL & CEREMADE, France

“Sparse weighted K-means for groups of mixed-type variables”

Friday November, 25 2022 12:30 to 1:30 pm (CET)

Dual formatESSEC Paris La Défense (CNIT), Room 237, and via Zoom, please click here (Password/Code : WGRisk)

TopicsAssessing the underlying structure of a dataset is often done by training a clustering procedure on the features describing the data. In practice, while the data may be described by a large number of features, only a minority of them may be actually informative with regard to the structure. Furthermore, redundant features may also bias the clustering, whether one speaks of redundancy in the informative or the uninformative features. This presentation aims at illustrating two sparse clustering algorithms designed for mixed data (made of numerical and categorical features). The proposed methods summarise redundant features into groups, and select the most relevant groups of features only in the clustering procedure. The performances and the interpretability of the methods are illustrated on several real-life data sets. This is a joint work with M. Chavent, M. Cottrell, J. Lacaille and A. Mourer.

 

Vendredi 25 novembre 2022
12h30 (GMT +1)
ESSEC Paris La Défense (CNIT)
2 Pl. de la Défense
92800 Puteaux
L'événement est organisé en ligne
Intervenants
Madalina OLTEANU
Professor in Applied Mathematics and Data Science
Université Paris Dauphine PSL and CEREMADE Paris, France

Madalina Olteanu obtained a PhD in Applied Mathematics in 2006. In 2007, she was appointed as Maître de Conférence at Panthéon Sorbonne University, where she was also a member of SAMM research team. Since 2020, Madalina is Full Professor of Applied Mathematics and Data Science at Paris Dauphine PSL University, and is member of CEREMADE research center.

Her current research interests are mainly focused on the study of temporal and spatial patterns in complex data, particularly in humanities and social sciences. The techniques she uses and investigates are related to time series analysis, Markov-switching models and change-point detection, feature selection in unsupervised learning, and self-organizing maps.

Localisation

ESSEC Paris La Défense (CNIT)

2 Pl. de la Défense
92800 Puteaux

Commentaires

Vous devez être connecté pour laisser un commentaire. Connectez-vous.

Vendredi 25 novembre 2022
12h30 (GMT +1)
ESSEC Paris La Défense (CNIT)
2 Pl. de la Défense
92800 Puteaux
L'événement est organisé en ligne
  • Ajouter à mon agenda