Description
Date depot: 10 juillet 2019
Titre: Semantic Data-Driven Approach for Merchandising Optimization
Directeur de thèse:
Bernard MERIALDO (Eurecom)
Encadrant :
Raphael TRONCY (Eurecom)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Intelligence artificielle
Resumé:
The general objective of this PhD consists in exploring and proposing new approaches leveraging on large volume of heterogeneous data that needs to be integrated and semantically enriched, and on recent progresses in machine and deep learning techniques, in order to harness both the increased variety of offers an airline can make to its customers as well as the knowledge it has about its customers with the ultimate goal of optimizing the conversion and purchase. The general objective of this PhD can be broken down into four main research
questions: 1) What content item (ancillary services, third party
content) should be recommended and personalized to each traveller? 2) When a recommendation should be made and for which communication channel in order to optimize the conversion? 3) How to bundle ancillary services and third party content and can we learn what come often together according to purchase logs? 4) How to model the recommender system using dynamic pricing as feature?
Doctorant.e: Dadoun Amine