Pascal Godbillot

Experience

• 

  École Centrale de Lyon

  Sept 2015 - Jan 2016

  Entrepreneurship Project - Business Creation

  Simulation of business creation around an innovative, viable and feasible idea. ‘Campus Création’ Competition. Key words : Entrepreneurship, Innovation, Market Research, Benchmark, Technical Feasibility, Business Model, Business Plan.

• 

  École Centrale de Lyon

  Sept 2016 - Jan 2017

  Industrial Project – Innovative provisioning methods by Machine Learning

  - Challenge current non-life provisioning methods in insurance and actuarial sciences.Sponsor : Consultancy firm in actuarial sciences.Key words : Provisioning, Actuarial sciences, Claim, Chain Ladder, Non-life Insurance, Machine Learning, CART, Random Forests. Kaggle : Allstate Claims Severity.

• 

  EDF

  Jan 2017 - Sept 2017

  Data Scientist Intern (R&D)

  Design, development and documentation of a python module for the prediction of performance loss of photovoltaic power stations.- Build a complete Machine Learning Pipeline- Improvement of the existing model via feature engineering, model selection and optimization.- Creation of a reporting tool (data visualization).Tools : Python, Pandas, Scikit-learn, Numpy, Scipy, SeabornInternship at the EDF R&D Lab Chatou within the PRISME department.

• 

  Mazars

  Oct 2017 - Mar 2018

  Financial Auditor Intern

  Shared internship with PANDA Guide (1 week a month) .- Audit missions for major groups in banking, industry, insurance and media sectors.- Expand my business acumen.Mazars is a global audit, accounting and consulting group.

• 

  PANDA Guide

  Oct 2017 - Mar 2018

  Machine Learning Intern

  PANDA Guide is a startup from the social and solidarity economy which offers an innovative solution for visually impaired and blind people.In the form of an audio headset equipped with a miniature video camera, the PANDA Guide solution relies on artificial intelligence to vocalize the user's environment. PANDA reacts to the voice of its user, and responds to his requests by describing his environment.- Development of a tool to identify text boxes within an image and then read this text.- Development of Deep Learning algorithms for identification of objects within an image.Tools : Python, Keras, OpenCV, Scikit-LearnI spend 20% of my time at PANDA Guide as part of my shared internship at Mazars. Voir moins

• 

  European Bioinformatics Institute | EMBL-EBI

  Jan 2018 - Jan 2018

  Data Scientist Intern

  Exploratory Data Analytics and Machine Learning in Bioinformatics to build up a Proof of Concept :- Retrieve unstructured data through multiple REST APIs to create a protein centric dataset (focused on genetic variation).- Exploratory analysis of this dataset.- Build up a "POC" to prove the usefulness of Machine Learning models in the analysis of genetic variations and their link with phenotypic traits, diseases.Tools : Spark, Python, Apache Zeppelin, Scikit-Learn, Pandas, Seaborn Voir moins

• 

  CybelAngel

  Mar 2019 - Jan 2023

  CybelAngel provides the only data leak detection platform that continuously and comprehensively monitors every layer of the internet.- Categorize, score, extract sensitive information from various web sources.- Develop and optimize machine learning algorithms with the rest of the Engineering team to be able to analyze in real time billions of documents per day.- Test models in a production environment and measure actual performance.- Tech vulgarization via data visualization and regular up-to-date meetings with product and cyber-analyst teams- Mentor and provide technical support to junior members- Share knowledge in the AI/ML field - Berlin Buzzwords 2022 international conference - https://www.youtube.com/watch?v=ORkl-pxGjBw DS tools : Python, ML packages, NLP packages, DataViz packagesMLOps tools: Git, CI/CD, Airflow, DBT, DataStudio, Datadog, TerraformGCP stack: BigQuery, Storage, Cloud Composer, PubSub Voir moins

  • Senior Data Scientist

    Sept 2022 - Jan 2023

  • Data Scientist

    Mar 2021 - Jan 2022

  • Junior Data Scientist

    Mar 2019 - Jan 2021
• 

  Quinten Health

  Jan 2023 - now

  Senior Data Scientist

  Integrated care and precision medicine solutions anchored in real-world data and powered by interpretable and actionable artificial intelligence.Working on several projects as a lead data scientist in small teams (3-5 people) composed of a project manager and data scientists. - Development of a rare diseases diagnostic library in real-world data settings. - Development of a NLP-powered web-based platform for identification, selection and pre-assessment of real-world data.- Bridging efficacy to effectiveness, anticipating value of treatment effect from RCT phase III to real-world using survival analysis. Career support through mentoring of data scientists. Technical stack: PySpark, Scikit-learn, Pandas, Transformers, Survival analysis packages. Docker, Kedro, Weaviate. Git, CI/CD Voir moins