Senior Data Scientist

The candidate will have responsibilities across the following functions:

Modelling and Analytics Delivery:

• Build, calibrate, and validate MMM models using historical media and business data.
• Quantify channel impact, measure ROI, and derive elasticity estimates.
• Develop response curves, saturation effects, and optimal spend recommendations.
• Integrate experimentation outcomes (lift studies, geo tests) to improve model robustness.

Data Management and Pipeline Development:

• Design end-to-end MMM data pipelines - including ingestion, transformation and QC.
• Manage large, multi-source datasets (media, pricing, distribution, promotions, seasonality).
• Automate recurring MMM runs and ensure reproducibility of analytics workflows.

Insights and Stakeholder Engagement:

• Translate complex model outputs into clear, business-friendly insights.
• Drive conversations with marketing, finance, and media teams on channel shifts.
• Present findings to senior stakeholders (CMO, growth leaders, digital teams).
• Recommend budget allocations and simulate what-if scenarios.

Operationalisation and Continuous Improvement:

• Build optimisation engines for budget planning.
• Monitor model performance and recalibrate based on new data.
• Ensure governance, documentation, and version control of MMM models.
• Collaborate with data engineers, product teams, media agencies, and business analysts.

Requirements:

• 5 to 8 years of experience in marketing analytics, MMM, media effectiveness, or econometrics.
• Prior experience in media agencies, consulting firms, or digital marketing analytics is a plus.
• Hands-on experience with MMM frameworks (Bayesian, frequentist, machine learning-driven).
• Advanced proficiency in Python or R for econometric modelling.
• Experience with cloud data environments (AWS/GCP/Azure).
• Knowledge of optimisation techniques (linear programming, gradient-based optimisers).
• Strong understanding of digital marketing KPIs across channels.
• Experience working with Nielsen, Kantar, Facebook Lift, or Google Geo-Experiments data.
• Exposure to MTA, incrementality testing, and customer journey analytics.

Technical and Modelling Skills:

• Strong econometric modelling: linear/non-linear regression, Bayesian MMM, hierarchical models.
• Expertise in ad-stock, diminishing returns, saturation curves, elasticity estimation.
• Solid understanding of causal inference (geo experiments, causal impact, synthetic controls).
• Experience with time-series modelling and lag structures.
• Proficiency in machine learning: regularised regression, gradient boosting, hybrid MMM.
• Strong statistical foundations: hypothesis testing, multicollinearity, variable selection.

Data and Engineering Skills:

• Advanced SQL, Python/R (statsmodels, PyMC, Stan, scikit-learn).
• Experience in data cleaning, transformation, feature engineering for media/marketing datasets.
• Handling multi-granular datasets (daily/weekly, campaign-level, spend, impressions).
• Familiarity with cloud platforms (GCP/AWS/Azure) and big-data tools (Spark, Databricks, BigQuery).
• Building automated model pipelines and reproducible codebases.

Marketing and Business Skills:

• Understanding of media channels (TV, Digital, Search, Social, OOH, Retail).
• Ability to compute ROI, ROAS, marginal ROI, and contribution splits
• Knowledge of attribution frameworks: MMM vs MTA vs experimentation.
• Strong storytelling: turning model outputs into actionable business recommendations.
• Budget optimisation & scenario planning expertise.