Global Ecommerce Data Scientist

ABOUT THIS ROLE

This exciting new role will give you the opportunity to apply your maths and statistics knowledge to turn data into revenue-driving analysis and insights. As a Data Scientist, you'll use your mathematical and statistical foundation to analyse customer behaviour, campaign performance, and ecommerce metrics. While prior marketing experience isn't required, you'll have the opportunity to develop deep expertise in customer and digital marketing measurement. The ideal candidate will have a quantitative degree, solid statistical knowledge, and a genuine curiosity for uncovering insights from complex datasets.

LOCATION

This role will be based in our Leeds office, and we offer a hybrid working pattern of 3 days in the office and 2 days WFH.

JOB ROLE AND RESPONSIBILITIES

• Support the development of statistical models, optimisation frameworks, and analytical methodologies to help drive ecommerce business objectives and strategic decision-making.
• Contribute to analytical projects across diverse business areas including optimisation models for pricing and promotional strategy, time series forecasting for demand and revenue prediction, marketing mix modelling (MMM) for marketing effectiveness measurement, and regression analysis for understanding customer behaviour and market dynamics.
• Support A/B testing and experimentation initiatives, assisting with experimental design and conducting statistical analysis to inform business decisions.
• Apply machine learning techniques for forecasting, clustering, and predictive analytics, learning to use appropriate validation techniques and hyperparameter tuning to ensure model quality.
• Use quantitative methods to help solve business problems by building analytical models and applying appropriate statistical and econometric techniques tailored to specific business contexts.
• Collaborate closely with team members on analytical projects, contributing to the development of statistical approaches and best practices using Python, R, SQL, and version control workflows.
• Help build and maintain data pipelines and ETL processes that support robust data infrastructure for analytics and modelling.
• Communicate findings to stakeholders by translating quantitative analyses into clear, actionable recommendations through data visualisations and presentations.