Join the team
fr LinkedIn YouTube

Client case for Total Energies

Industrialization of Marketing Data Use Cases
Location
Paris
Project's functional area
The mission at TotalEnergies involves end-to-end Data Science and Data Engineering support, fully deployed on the Google Cloud Platform (GCP), serving the marketing and data teams.
Technological environment
Languages & Development
Java, React, Microservices Architecture, Python

Data Science & Machine Learning
Pandas, Statistical Analysis, Predictive Modeling, Explanatory Modeling, Machine Learning, Causality & Model Explainability

Data Engineering
ETL Pipelines, Data Ingestion (APIs, Web Scraping, Public Sources), Textual and Tabular Data Processing

AI & Intelligent Agents
Autonomous Data Agents, Multi-Agent Systems, Generative AI, Automation of Data Collection and Analysis

Cloud & Platform
Google Cloud Platform (GCP), BigQuery, Vertex AI, Data Pipelines, Managed APIs & AI Services

Data Visualization & Reporting
Streamlit, Interactive Business-Oriented Dashboards
Methodology
SCRUM
Detailed description of the project

The project team consists of 2 Data Scientists and 1 Data Engineer, working in a coordinated manner across the entire data value chain.

Development & GCP Cloud

  • Python application development

  • Creation of interactive business interfaces

  • Deployment and operation of solutions on GCP (data services, pipelines, APIs, security)

  • Close collaboration between Data Scientists and Data Engineer to industrialize solutions

Data Science – 2 Data Scientists

  • Analysis of marketing business needs and scoping of use cases

  • Design and implementation of advanced Marketing Mix Modeling (MMM) and complementary models (ABM)

  • Utilization and adaptation of advanced open-source solutions

  • Development of explainable and interpretable models

  • Analysis of results, production of insights, and business recommendations

  • Contribution to reporting results via user-friendly interfaces

Data Engineering – 1 Data Engineer

  • Design and implementation of ETL pipelines on GCP

  • Automated collection of internal and external data (APIs, scraping)

  • Data structuring, cleaning, and historization

  • Setup and management of analytical databases (BigQuery)

  • Orchestration and monitoring of data processing workflows

  • Ensuring performance, reliability, and security of data flows

Back to list