Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier. (2017-2018 à 2018-2019)

In the past decade, retailers have experienced a massive surge in information ranging from how their productsx000D
sell and which products their customers prefer, to how their promotional campaigns perform. This dramaticx000D
change in data availability was mainly due to advances in the Internet-of-Things and data warehousing,x000D
allowing millions of customer transactions to be logged in big data centers. This abundance of information,x000D
however, cannot easily translate into benefits for retailer and customer, unless it is rigorously analyzed to guidex000D
business decisions. It comes as no surprise that Big Data analytics are now becoming a business imperative inx000D
the realm of retail, with more and more retailers applying data mining technologies to transform theirx000D
processes, from product recommendations to sales forecasting. Still, a large amount of the raw data available tox000D
retailers is incomplete and generic to justify meaningful analysis. For example many products are onlyx000D
characterized by type, price, color etc., whereas information that tells if the product is more appealing tox000D
specific ages, or that is more of a luxury product or not, is usually absent. It is entirely up to the manual effortx000D
of human experts to identify these "hidden" attributes, but this incurs significant costs and delays to the retailerx000D
or any third party that offers services on big data analytics. The goal of this work is to develop novelx000D
methodologies based on machine learning technologies to automatically discover these hidden attributes withx000D
minimal human intervention. These methods will learn non-obvious information by mining text and reasoningx000D
around images associated with each product, combining techniques from Natural Language Processing andx000D
Computer Vision. Through this process one can produce enriched product ontologies that allow for efficientx000D
market-driven analytics.