Context
A leading consumer electronics company in France needed to centralize customer review data and scale its analysis using AI and dashboards.
Approach
Airflow-to-BigQuery pipelines collect data via APIs from multiple providers and collection systems, supported by GCP governance and NLP models (Hugging Face, BERTopic, QA, and LLMs). Results are delivered through Tableau dashboards and distributed internally to the relevant teams.
Impact
Customer service can instantly find classified topics and escalated alerts while tracking requests more accurately. The product team identifies and anticipates defects and logistics issues, while the legal team can better anticipate disputes.
What we delivered
- Data collection from multiple APIs (mystery shopping, CRM, social media, and reviews), orchestrated by Airflow.
- Cloud policies covering team segmentation, data localization, security, and best practices.
- Analysis and classification pipeline with LLMs.
- NLP pipelines for similarity, sentiment, and topic analysis across multiple languages.
- Design and implementation of dashboards used daily by the Customer & Market insights team.
- Documentation and training for data and business teams.
- Automated insight exports to marketing business units and agencies.
Critical work deserves more than generic software.
Start with a real use case, the stakeholders involved, and the available data to identify the next useful step.
FDTI / Contact
Let's keep it simple.
We only use your contact details to reply: no newsletters, no unsolicited outreach, and no commercial sharing with third parties.