Remote

Data Science Intern (Modelling)

Build and test quantitative models that explain and improve how fashion assortments perform.

As a Data Science Intern focused on algorithmic retail, you will work on developing and evaluating quantitative models that support fashion planning decisions. Your work will focus on analysing retail time-series data across sales, inventory, pricing, and assortment structure to understand demand patterns, performance drivers, and structural inefficiencies.

You will help design and test models that separate demand effects from execution effects, quantify trade-offs between breadth, depth, and price, and support scenario-based analysis of alternative assortment strategies. This includes working with historical season data, building metrics and optimisation logic, running simulations, and validating model outputs against real outcomes.

The role emphasises applied modelling over reporting. You will work closely with research and engineering teams to translate analytical concepts into decision-support tools used by merchandisers and planners.

What you will learn

How to model retail demand and performance using real-world fashion data
How to work with time-series, panel data, and constrained optimisation problems
How to design and evaluate algorithms for assortment structure and planning decisions
How to test models against historical outcomes and interpret results
How quantitative insight is translated into practical decision guidance

Who should apply

Students or recent graduates in data science, applied mathematics, statistics, economics, or related fields
Strong interest in modelling, optimisation, and analytical problem-solving
Comfortable with Python and quantitative data analysis libraries
Interested in applying rigorous methods to commercial and creative decision-making

Career path

This internship can lead to junior data scientist, quantitative analyst, or planning science roles, with increasing responsibility for model design and evaluation. The role is experience-focused and unpaid, with the possibility of part-time or full-time employment based on performance and future team needs.

‍