Serge-Henri C.

DATA SCIENTIST

488 euro

My experience

More

Crédit Agricole Technologies et Services, FreelanceNovember 2019 - March 2020

As a Pipeline Chapter member, my role is to guide teams to use XLRelease tool for their CD up to production in the context of the company transformation.
More

AUSYJanuary 2018 - February 2019

I was working as a consultant at Societe Generale in Paris (major french bank) for AUSY (tech company).
The first purpose of the mission was to develop APIs (python, flask RESTPlus) for dashboards and reports. The second was to industrialize predictive maintenance pocs via APIs.

The ETL pipeline started with data extraction from a datalake (Hadoop - HDFS), transformation and update (pyspark, python scripts, crontab) and load in an elasticsearch. APIs (Python Flask RESTPlus) were developed in order to collect the data from ES and a posgresql DB which was sent to the front (Angular) to display interactive dashboards.
The APIs were developed and tested on DEV and UAT VMs and finally deployed in production.

Methodology: Agile - Scrum
More

Cartapapa, FreelanceJuly 2017 - December 2017

The aim of this mission was to research and develop an innovative inventory methodology for a trading card game based on image recognition.

Data was collected thanks to web scrapping (Beautiful Soup) and techniques such as simple logistic regression, CNN (keras) or (py)tesseract (ocr) were investigated.
More

IndépendantFebruary 2016 - November 2016

The aim of this work was to coordinate a team of volunteer entrepreneurs in Chengdu, China, to organize a networking between Western and Chinese companies in the city.

I also had the opportunity in this period to provide help to these entrepreneurs to optimize the processes in their business (especially high quality fast food business).
More

S2DS (Science to Data Science)August 2016 - September 2016

Intense 5 weeks data science fellowship involving project work and lectures on current data science topics such as SQL, MongoDB, Python, Pandas, Machine Learning and Statistics, as well as a wealth of business topics including Finance, Strategy and Marketing.

Worked on a project with Row Analytics involving aggregation and analysis of big DNA mutation datasets, using Python (inc. Pandas), mongoDB, Natural Language Processing (NLP) and visualization tools such as Neo4j.
More

AREVAMarch 2010 - August 2010

This internship purpose was to understand in a better way how a carbochloration reactor worked and which input parameters could be changed in order to optimize the reaction. This was performed thanks to numerical simulations and the analysis of the output data.

My stack

Web Scraping, Tesseract, SQL, Spark, Scrum, Scikit-Learn, Python, PostgreSQL, Pandas, Neural networks, Neo4J, Natural Language Processing (NLP), MS Office, MongoDB, Matplotlib, Matlab, Marketing Strategy, Marketing, Machine Learning, LaTeX, Keras, HDFS, Hadoop, Git, Fortran, Flask, ETL, ElasticSearch, Deep learning, Data Science, Data analysis, Crontab, Continuous Integration, Continuous Deployment, CodePipeline, C/C++, Bootstrap, BeautifulSoup, Artificial Intelligence, Agile