Context and assignment
Two data science solutions: Text2SQL & FinOps forecasting.
Development of a Text2SQL chatbot on technical documentation and a forecasting app dedicated to FinOps challenges, using state-of-the-art Deep Learning and GenAI. Turning POCs into robust, scalable solutions.
The challenge
What was at stake
For SNCF, the assignment covered: “Two data science solutions: Text2SQL & FinOps forecasting”. This kind of programme involves business departments, IT and data teams at the same time: it has to deliver quickly without weakening existing systems, and leave behind practices that hold once the assignment ends.
The relationship
Visian since 2020
SNCF Connect, a very high-traffic consumer platform, calls on Visian for quality, product and data. Visian has worked there since 2020, with 24 assignments for SNCF Connect.
Expertise involved: Full-stack development, QA, agile, data analysis, Python big data.
Deliverables
- Replatforming of Python big data tools (OUI.sncf)
- Technical product ownership
- QA engineering in Paris and Nantes
- Data analysis
Team and duration
Duration, team and scope
- Duration: since 2020.
- Team: a multidisciplinary Visian team, sized to each phase, covering full-stack development, QA, agile, data analysis, Python big data.
- Scope: Replatforming of Python big data tools (OUI.sncf); Technical product ownership; QA engineering in Paris and Nantes; Data analysis.
Approach
How Visian worked
- Scope: workshops with the departments involved, assessment of the existing set-up, prioritisation and deliverables approved in steering committee.
- Build: delivery in short iterations, shared milestones and project governance with the client teams.
- Handover: adoption support, documentation, skills transfer to in-house teams and move to run.
Results
Measured results
Scope
Methods and technologies
Expertise involved