ENBIS-19 Post-Conference Course: Random Forests5 September 2019; 09:00 – 13:00
Thursday, 5th September, 9:00-13:00
Jean-Michel Poggi (Paris-Descartes Univ. and Lab. Maths Orsay, Paris Saclay University, France)
This tutorial is an introduction to Random Forests and is aimed at a broad audience of statisticians. Based on decision trees combined with aggregation and bootstrap ideas, random forests were introduced by Breiman in 2001 and are one of the most powerful and widely used statistical learning methods. Indeed, they are a powerful nonparametric statistical method allowing to consider in a single and versatile framework regression problems, as well as two-class and multi-class classification problems. Variable importance index allows in addition to propose a ranking of explanatory variables and to define a variable selection strategy involving ranking and a stepwise ascending variable introduction strategy. The provisional table of contents of the course is:
- Classification and Regression Trees (CART)
- Random Forests
- Variable importance
- Variable selection
- Practice session
- An application in industry
- Random Forests for Big Data
Short biography of the lecturer
Jean-Michel Poggi is Professor of Statistics at Paris-Descartes University and Lab. Maths Orsay, Paris Sud University, in France.
His research interests are in time series, wavelets, tree-based and resampling methods, applied statistics. Research activities combine theoretical and practical contributions together with industrial applications (mainly environment and energy) and software development.
His publications combine theoretical and practical contributions together with industrial applications and software development.
He is Associate Editor of three journals: Journal of Statistical Software, CSBIGS (Case Studies in Business, Industry and Government Statistics) and Journal de la SFdS.
More information can be found at: http://www.math.u-psud.fr/~poggi/