Key Responsibilities
- Build and refine price elasticity models, promotional uplift models, and demand forecasting frameworks using retailer POS/sell-out data/syndicated data/Sell-In data
- Build and refine price and promotion optimization models
- Contribute to the development of a reusable, parameterized modelling framework that can be deployed across multiple markets with minimal rework
- Work with RGM SMEs to translate commercial questions into modelling briefs and validate outputs for commercial sensibility
- Collaborate with data engineers to define data schemas, feature requirements, and model-ready dataset specifications
- Document modelling assumptions, validation results, and known limitations clearly for both technical and business audiences
- Support deployment and handover of models to client teams, including technical documentation and user guides
- Proactively flag data quality issues and modelling risks to the project lead
Qualifications — Required
- Master's or equivalent in Statistics, Economics, Data Science, Operations Research, or a related quantitative field
- 4–14 years in applied data science, with at least 2 years focused on pricing analytics, promotion effectiveness, or revenue management in CPG or Retail
- Hands-on experience building price elasticity models and/or promotional lift/uplift & Optimization models in a commercial context
- Familiarity with sell-out or POS data from syndicated providers (Nielsen, IRI/Circana) or direct retailer feeds
- Proficient in Python (scikit-learn, stats models, XGBoost) and SQL
- Experience with cloud analytics platforms (Databricks, Snowflake, or equivalent)
- Ability to communicate modelling results clearly to non-technical stakeholders
