Pricing Data Scientist

Description

Castrol is one of the world’s leading lubricant brands, serving customers and consumers in the automotive, marine, industrial and energy sectors. Castrol brands are recognised globally for their premium quality and high performance, shaped by the company’s commitment to innovation and cutting-edge technology. With products sold in more than 150 countries, Castrol has helped keep things moving on roads and racetracks, air, sea, and space for over 125 years.

Whether you're just starting out or ready for your next big move, you're in the right place to explore an exciting career with Castrol.

Castrol’s Global Pricing Team helps the business make pricing decisions informed by their impact on revenue and profit, and you’ll help build its data science and operations research capability alongside its existing pricing and commercial expertise. Reporting to the Pricing Data Science & Automation Manager, you’ll work with colleagues across Pricing, Sales, Finance and Marketing to turn commercial questions into models and tools people can use.

Key tasks

Build and refine models for demand forecasting, price sensitivity, willingness to pay and price optimisation, connecting your analysis to real pricing decisions.

Work through analytical problems from end to end: for a price-elasticity question, for example, help define the problem, develop the methodology, connect the data sources and automate the delivery of results.

Compare pricing and portfolio scenarios to understand their likely impact on revenue and margin.

Analyse how discounts, trade spend, product mix and customer segments affect the revenue the business retains.

Turn analysis into reusable tools and automated workflows that reduce repeated manual work and make processes faster and more reliable.

Explain your methods, results and recommendations clearly, so your models stand up to scrutiny and colleagues can use the findings.

Work with pricing colleagues to understand how your recommendations inform decisions and, where possible, trace their impact on business performance.

Experience required

A strong foundation in mathematics and statistics, with experience applying data science or operations research to analytical problems.

A university degree or equivalent experience, with evidence of your quantitative and modelling skills through study or practical work.

An understanding of regression, machine learning, segmentation and optimisation techniques.

Proficiency in an analytical programming language such as Python or R, alongside strong SQL and data manipulation skills.

Experience working with large datasets and translating business questions into analytical approaches.

The ability to build models and turn them into reliable, repeatable tools, beyond producing reports or dashboards.

The ability to automate analytical processes, from preparing data to delivering usable outputs.

Clear written and verbal communication, including the ability to explain how you reached a result and what it means.

You don’t need to arrive as a pricing expert. Pricing, revenue management or commercial analytics experience would be useful, but it isn’t essential: you may have developed the relevant skills in banking or another industry, and the team can help you learn the pricing side.

Experience with tools such as Power BI is useful alongside those deeper modelling skills. Familiarity with APIs and automation tools would also help, but these are not essential requirements.