Freelancer profile translated to English.

Description

Experienced data science professional, I have developed technical and functional expertise through various missions. Currently a Senior Data Scientist, I centralize churn-related analyses and help Actuarial, Finance, Marketing, and Sales teams reduce churn. I technically lead a team of three collaborators and use tools such as AWS Cloud for portfolio segmentation and churn score development. My role also includes technical support and training on technologies such as R, Python, Spark (Sparklyr and Pyspark), and Git, skills that I have also strengthened by publishing articles and participating in strategic work related to the health crisis.

My experience as Lead Data Scientist and Technical Manager Data Scientist has allowed me to master machine learning algorithms (GBM, RF, XGBOOST), dimension reduction techniques (PCA, MCA, FCA), and deep learning (TensorFlow, Keras, Pytorch, Transformers). I have also developed skills in data analysis and visualization, report automation, and the creation of R packages to improve productivity. My expertise extends to the use of tools such as SQL, Git, Docker, and model versioning with MLFLOW, ensuring robust and scalable solutions tailored to business needs.

Languages

English
Fluent
French
Native or bilingual

Workplace preferences

Can work on-site

Paris 16e Arrondissement (up to 50km), Paris (up to 30km)

SantéVet
Lead Data scientist
BANKING AND INSURANCE
July 2022 - Today (3 years and 11 months)
Paris, France
My mission is to centralize all analyses related to churn and to help the various business lines (Actuarial, Finance, Marketing and Sales) in their contribution to reducing churn
Portfolio segmentations, Churn score under AWS Cloud
Technical lead of a team of 3 collaborators
MLOps Python R Cloud AWS AWS SageMaker Docker AWS S3 AWS EC2
UNEDIC
Senior Data scientist
BANKING AND INSURANCE
September 2019 - June 2022 (2 years and 10 months)
Paris, France
In charge of the technical support and skills development of the Unédic team on new data analysis tools, bringing my expertise in studies and analysis work.
Development of Shiny datavisualization applications
Development of R packages internal to Unedic
Implementation of automated reports with Rmardown
Training and technical support on R, Python, Spark (Sparklyr and Pyspark) and Git.
Publication of several articles on the typology of job seekers and member of the team dedicated to work on Partial Activity in the context of the Covid health crisis
Python PySpark R Sparklyr Bitbucket
Secteur de l'Energie
Lead Datascientist
ENERGY AND UTILITIES
February 2018 - September 2019 (1 year and 7 months)
Levallois-Perret, France
Lead Datascientist at Marketing

Responsible for statistical analysis, modeling and monitoring of KPIs for B2C and B2B segments at Eni, as well as popularizing statistical techniques for the Marketing team.

Development of churn, cross-sell and service propensity scores for offers that have helped reduce churn by 10% and increase cross-sell by 15%
Detection of different profiles of customers in the portfolio through a segmentation allowing to address our customers according to their typology
Creation of R packages to improve productivity and reproduction of analyses and studies
Technical lead of a team of 3 people.
Machine Learning Data science R Shiny H2o Data mining Data visualisation Scikit-learn Python MLflow