Requirements
* Significant experience as a Data Scientist, with a background in marketing analytics, ecommerce, or a loyalty or membership-driven environment
* Strong Python proficiency for data manipulation, statistical modelling, and machine learning, alongside advanced SQL skills and experience with dbt
* Solid grounding in statistical methods including regression, causal inference, and experimental design, with hands‑on experience building and interpreting A/B tests
* Practical experience building predictive models, particularly in retention or customer engagement contexts, with working knowledge of MLOps practices and model deployment pipelines
* Experience collaborating with CRM or lifecycle marketing teams, with the ability to shape model outputs into actionable recommendations
* The ability to communicate complex findings clearly to non‑technical stakeholders, and to build reusable data products that others can act on independently
* Familiarity with CLV modelling frameworks such as BG/NBD, Pareto/NBD, or ML‑based approaches would be a bonus, but is not essential
What the job involves
* We’re looking for a Data Scientist, Decision Sciences, with a focus on retention and member engagement
* You’ll evaluate pipelines and results of retention models and identify improvements in outputs to improve the retention strategy
* You’ll partner closely with stakeholders across the organisation, translating complex questions into well‑designed solutions, and communicating your findings in ways that land with both technical and non‑technical audiences alike
* Design, develop, and iterate on machine learning models across the member lifecycle, with a particular focus on retention, churn prediction, and customer lifetime value
* Evaluate existing model pipelines and outputs, identifying and implementing improvements to increase accuracy and business impact
* Work closely with the CRM Lifecycle team to connect model outputs to retention strategies, capturing feedback and incorporating it back into model development
* Build forecasting models and marketing mix models to support financial planning and commercial decision‑making
* Translate ambiguous business problems into well‑defined data science approaches, conducting deep‑dive analyses across member behaviour, commercial performance, and marketing effectiveness
* Build and interpret A/B tests and holdout experiments to support evidence‑based decision‑making
* Create dashboards and visualisations that help the wider organisation understand model results and progress
* Act as a trusted partner to business and analytics stakeholders, understanding their goals and proactively identifying where data science can add value
#J-18808-Ljbffr