Skip to Main content Skip to Navigation
Habilitation à diriger des recherches

Sur les traces du futur : entre comprendre et predire

Armelle Brun 1
1 KIWI - Knowledge Information and Web Intelligence
LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Empirical modelling, which relies on data, also referred to as traces, is an approach for modelling phenomena, systems or objects. It has the characteristics of modeling the “reality” of these phenomena. The researches I have conducted are dedicated to both descriptive and predictive modelling. They focused on robustness, complexity and quality of the models, but also on the identification of triggering or explanatory factors in data. My contributions have been applied and validated in the frame of e-commerce and, more recently, on e-education through the use of traces of behavior, of preferences, etc. My future research goes a step further and will focus on prescriptive modelling : what can be done to reach a given objective ? Some considerations related to algorithms that can explain themselves and that are transparent (explainable AI), as well as the management of multiple sources of data will be studied.
Document type :
Habilitation à diriger des recherches
Complete list of metadata

Cited literature [254 references]  Display  Hide  Download
Contributor : Armelle Brun <>
Submitted on : Sunday, July 8, 2018 - 6:46:16 AM
Last modification on : Monday, October 19, 2020 - 11:03:42 AM
Long-term archiving on: : Tuesday, October 2, 2018 - 7:29:50 AM


Files produced by the author(s)


  • HAL Id : tel-01832540, version 1



Armelle Brun. Sur les traces du futur : entre comprendre et predire. Intelligence artificielle [cs.AI]. Université de Lorraine, 2018. ⟨tel-01832540⟩



Record views


Files downloads