Freelancer profile translated to English.

Description

Big Data specialist engineer, with 3 years of experience, I am at your disposal for any data analysis and data science project. My expertise covers the following areas:

- Collection from any type of environment and with the most common languages (flat files and databases with SQL, data lake with spark, web with Python)

- Data exploration and preparation with Python and its dedicated libraries (pandas, numpy)

- Modeling with usual machine learning algorithms (linear and logistic regression, KNN, decision trees, random forests with scikit-learn) and more advanced ones (neural networks with tensorflow/keras)

- Model evaluation with usual techniques (confusion matrix, log loss, least squares method)

- Notions on SOAs (REST API) and the Hadoop ecosystem (HDFS, YARN, Hive, Hbase, Kafka) and Spark

- Data governance (knowledge of GDPR, dissemination of good usage practices, metadata modeling, definition of quality tracing indicators)

- Project management using Agile methodology (SAFe framework)

Languages

French
Native or bilingual
English
Fluent

Workplace preferences

Can work on-site

Ivry-sur-Seine (up to 50km)

Air France
Data analyst/scientist
TRANSPORTATION
September 2019 - December 2022 (3 years and 4 months)
Roissy-en-France, France
Within the Customer Data Management unit of the Commercial department, data scientist/analyst missions for various internal clients. Projects carried out using agile methodology:
- Prediction of revenues generated by the company's physical agencies with a view to their potential closure. Deliverables: data analysis with Pandas, machine learning model (linear regression) coded in Python (scikit-learn)
- Prediction of the profitability of rental, a clothing and accessories rental service in airports. Deliverables: data analysis with Pandas, machine learning model (logistic regression) coded in Python (scikit-learn)
- Monitoring of transactional data quality on the data lake. Deliverable: Python script for Spark to query, format, and analyze files stored on Hadoop HDFS
- Verification of transactional data quality on the Vantage analytical platform. Deliverable: SQL queries
- Documentation of reference data. Deliverables: business glossaries, GDPR code of conduct, data model
Agile methodology Pandas Data science Machine learning Python Spark Data Lake GDPR
Air France
V.I.E Pricing and Business Intelligence Analyst
TRANSPORTATION
January 2018 - June 2019 (1 year and 6 months)
Atlanta, United States
Within the joint venture with Delta, pricing analysis and business intelligence mission for the United States to Africa, Middle East, and Asia scope.
3300 origin-destination combinations, annual turnover: $800 million
- Data collection with SAP Business Objects
- Development of decision support tools to improve the profitability of the joint venture. Deliverables: Microsoft Excel tool (VBA) for task prioritization, optimal price prediction model considering strategy and competition based on machine learning (clustering, linear regression)
- Performance monitoring. Deliverables: Microsoft Excel dashboards
- Relationship management with the subcontractor based in India. Deliverables: documentation of procedures and tools created with Microsoft Office