Menu

Hichem BANNOUR

Paris

En résumé

I am currently Director R&D, at Marin Software. Before joining Marin, I was the head of Research and Development at Social Moov, a leading french company specialized in social marketing. The current main tasks I'm involved in are: developing machine learning algorithms for recommender systems, for CTR prediction, and automatic bidding; proposing solution for semantic data analysis; and make valuable use of the big data generated by the Marin platform.

Regarding my scientific background, I obtained my Ph.D. degree in computer science from the MAS (Applied Mathematics and Systems) laboratory of Ecole Centrale Paris, France, in early 2013. Afterwards, I held the position of a research engineer at the CEA-List Vision & Content Engineering laboratory, Atomic Energy Commission, France.

My main research interests include image semantics modeling, image annotation, multimedia information retrieval, image and data mining, statistical machine learning, and ontological engineering. I am also interested in digital media processing, semantic analysis of digital content, recommender systems and more generally machine learning for digital marketing.

Mes compétences :
Java
MFC
Data mining
C/C++
Machine Learning
Python
Traitement d'images
Matlab/Simulink
Php/mysql
Moteur de recherche d'information
Lucene
Unix/Linux
MongoDB

Entreprises

  • Marin Software - Distingushed Engineer, Data Science

    Paris 2016 - maintenant San Francisco, Ca

  • Marin Software - Director, R&D

    Paris 2015 - 2016 I am currently Director R&D, at Marin Software. The current main tasks I'm involved in are: developing machine learning algorithms for recommender systems, for CTR prediction, and automatic bidding; proposing solution for semantic data analysis; and make valuable use of the big data generated by the Marin platform.

  • Social Moov - Head of Research & Development

    Paris 2013 - 2015 My main task in Social Moov is to develop the R&D activities of the company. These include : - providing a roadmap for R&D projects, seeking funding for our research projects, hiring appropriate persons to fill the job, and managing the R&D team

    The main R&D projects that I lead at Social Moov are as follows:
    - TV Synchro: a software allowing to detect all commercials diffused on tv channels, i.e. automatically retrieve new commercials, index them and recognize them any time they are diffused again.
    - User retargeting: processing the stream of social data in order to gather valuable information about user preferences and their behaviours on social networks.
    - ContAds: Semantic analysis of textual social content, i.e. NLP of Facebook comments and trend detection over the Twitter stream.
    - SmartBiding: building heuristic rules in order to manage effectively (and automatically) advertising campaigns on social networks, i.e. set up an effective RTB (Real Time Bidding) algorithm and efficiently handle the advertising campaigns (play/pause/stop according to achieved stats).
    - Big data processing: proposition of scalable algorithms which cope with large-scale and heterogeneous data.

  • CEA Saclay - Research and Development engineer

    Gif-sur-Yvette 2013 - 2013 I was working on an European project named Multimedia And User Credibility Knowledge Extraction (MUCKE). MUCKE addresses the stream of multimedia social data with new and reliable knowledge extraction models designed for multilingual and multimodal data shared on social networks. It departs from current knowledge extraction models, which are mainly quantitative, by giving a high importance to the quality of the processed data, in order to protect the user from an avalanche of equally topically relevant data. It does so using two central innovations: automatic user credibility estimation for multimedia streams and adaptive multimedia concept similarity. Credibility models for multimedia streams are a highly novel topic, which will be cast as a multimedia information fusion task and will constitute the main scientific contribution of the project. Adaptive multimedia concept similarity departs from existing models by creating a semantic representation of the underlying corpora and assigning a probabilistic framework to them.

  • Ecole Centrale Paris, Laboratoire MAS. - Doctorant-Chercheur

    2009 - 2013 Implémentation d’un moteur de recherche d’images pour un partenaire industriel.
    Implémentation d’un moteur d’annotation sémantique d’images.
    Publication dans des conférences et des journaux internationaux.
    Compétences: Multimedia, recherche d'information, machine learning, data mining, systèmes à base de connaissances, ontologies, classification.

Formations

Pas de formation renseignée

Réseau

Annuaire des membres :