Few words about me

Graduated from the University 1 Claude Bernard of Lyon (co-accredited with Lyon Ecole Centrale and Lyon Ecole Nationale Superieure), I am an engineer in Machine Learning and more generally in the field of Data.
Beyond this expertise, I have worked on various projects that have used skills specific to computer science such as robotics, embedded, signal processing, information retrieval, and so on.

Background

I began my university career by studying architecture and construction management (BTS). Accompanied by my first professional experiences, this training revealed to me the management of teams, deadlines, contracts, and responsibilities. I had the opportunity to work and to be trained with extremely innovative companies, whose main focus was the numerical modeling of these constraints before the realization of the project. This led to the identification of critical points of the projects, their resolution, and consequently their reduction in the long term systematically.

These circumstances led me to a certain interest in different modeling methods and consequently to a further study in computer science. After a DUT, a Bachelor and a Master Degree in computer science with a specialization in Mathematics and Artificial Intelligence, I follow my passion for modeling, data and systemic in order to offer one step ahead to the people I work with.

Services and stack

Data Extraction

Every data project requires data and therefore starts with data acquisition. The method of acquisition varies depending on the project: scraping, API request and sensor management are examples.

Data Engineering

The acquired data must be cleaned, formatted and finally stored. Depending on the characteristics of the collected data, SQL or noSQL databases are required for this type of task.

Data Analysis

Data mining allows us to discover exploitable patterns in order to transform them into added value for our project. A strong background in mathematics may be necessary for this step.

Data Visualisation

Although it can be very easy to create visual representations, it is much more difficult to create good ones. Tableau is a tool that allows to make excellent adapted visualisations.

Data Exploitation

Once an initial analysis has been carried out and a proof of concept satisfied, it may be interesting to automate decisions and more generally the transfer of knowledge from new cases. Numerous libraries allow to achieve this (SKLearn, PyTorch...).

Production and Deployment

A rocket is nothing without its launcher. When you want to deploy a machine learning model in production, it is necessary to use technologies such as AWS or Microsoft Azure to maintain it.

Research Data Scientist Intern
(End of study Internship)

at LIRIS (Lyon), from 01/02/22 to 31/07/22.

Automatic discovery of scholar article typology

End of study Internship topic: "Automatic discovery of the role of scientific article based on a dynamic citation network enriched by citation context".

  • Data extraction and storage in noSQL database.
  • Network generation, transformation and topological analysis.
  • Feature selection, clustering and classification.
  • Semantic analysis and NLP (NLTK, TF-IDF, word2vec, doc2vec).
  • Exploration of complementary methods (graph2vec, node2vec, edge2vec, GCN/GNN (Graph Neural Network)).

    Skills: Python, Machine Learning, Graphs, NLP, Shallow Networks, Clustering, Gensim, NetworkX, GePhi, Scikit-learn, Pandas, Embeddings, Graph Neural Networks (GNN)

Student
(Student Research Project)

at Claude Bernard University Lyon 1 (Lyon), from 01/11/20 to 31/06/21.

Graph Data modelling and exploration

Exploratory study of a citation network of scientific publications enriched with contextual elements.

  • Extraction of data and metadata from a corpus of scientific articles in XML format.
  • Generation of the citation network.
  • Semantic enrichment of the network by the context of the citation.
  • Analysis of the structure and nature of the network.

    Skills: Python, Machine Learning, Graphs, NLP, NetworkX, GePhi, Scikit-learn, Pandas

Student
(Student Research Project)

at Claude Bernard University Lyon 1 (Lyon), from 01/02/20 to 31/05/20.

Spatial and statistical exploration of avalanches in the Alpine region

Design and participation in the development of a data visualization website for spatial and statistical exploration of avalanches in the Alpine region.
My responsibility within the workgroup: Coordination and management of the project and the team, web scraping, storage, formatting, data cleaning, statistical analysis.

  • Collection (web scraping) on specialized sites.
  • Storage, formatting and cleaning of raw data in order to:
    • Exploit them on a visual web interface, thus specifying the zones with high avalanche frequency and consequently at risk.
    • Statistical analysis of the data in order to determine the environmental factors that favor the triggering of avalanches.

      Skills: Python, Machine Learning, Statistics, Scraping, Selenium, Leaflet, Data Visualisation, Scikit-learn, Pandas, Beautiful Soup

    • Interested in my profile?

    Download a PDF resume