Sumit Sidana - Systèmes de recommandation pour la publicité en ligne

Organized by: 
Sumit Sidana
Sumit Sidana
Detailed information: 


Jury :

  • Patrick Gallinari , LIP6, Sorbonne Universite (Rapporteur)
  • Josiane Mothe, Institut de Recherche en Informatique de Toulouse (IRIT) (Rapporteure)
  • Sihem Amer-Yahia, Centre National de la recherche scientifique (CNRS) (Examinateur)
  • Romaric Gaudel, ENSAI (Examinateur)
  • Gilles Vandelle, Kelkoo (Examinateur)
  • Massih-Reza Amini, Université Grenoble Alpes (Directeur de these)
  • Charlotte Laclau, Université Jean Monnet (Codirectrice de these)



This thesis is dedicated to the study of Recommendation Systems for implicit feedback (clicks) mostly using Learning-to-rank and neural network based approaches. In this line, we derive a novel Neural-Network model that jointly learns a new representation of users and items in an embedded space as well as the preference relation of users over the pairs of items and give theoretical analysis. In addition, we contribute to the creation of two novel, publicly available, collections for recommendations that record the behavior of customers of European Leaders in eCommerce advertising, Kelkoo\footnote{\url{}} and Purch\footnote{\label{purch}\url{}}. Both datasets gather implicit feedback, in form of clicks, of users, along with a rich set of contextual features regarding both customers and offers.  Purch's dataset is affected by popularity bias. Therefore, we propose a simple yet effective strategy on how to overcome the popularity bias introduced while designing an efficient and scalable recommendation algorithm by introducing diversity based on an appropriate representation of items. Further, this collection contains contextual information about offers in form of text. We make use of this textual information in novel time-aware topic models and show the use of topics as contextual information in Factorization Machines that improves performance. In this vein and in conjunction with a detailed description of the datasets, we show the performance of six state-of-the-art recommender models.