Data Scientist (Credit) - Car Finance

Start free →

Or apply yourself on the official page →

About the role

We’re on a mission to make migration easy. We started building Marshmallow in 2017. Since then, we’ve grown from 3 to 700+ people, gained unicorn status, raised ~£140M over three funding rounds, turned profitable, insured millions of drivers and lent millions in car loans. But we’re only just getting started. Our goal is to become one of the largest financial services providers in the world. Over the next 10 years we’ll grow exponentially, not only by scaling our existing products, but also by building new ones. To achieve our goals we need incredibly ambitious, commercially driven people who never settle for ‘good enough’. Marshmallowers are hungry for autonomy and ownership, and would rather improve than coast. Everyone raises standards and has an impact, with a focus on collective success over self-interest. We’ve created an environment where curious, tenacious people win and grow together. If that sounds motivating, this could be the place for you. London (hybrid, 3 days in office)   Car Finance at Marshmallow Marshmallow is opening up access to credit to migrants, bringing a brand new product to market which provides newcomers to the UK with fairly priced car finance for the first time. Our Car Finance team is building a new generation lending platform from the ground up, making it simple, transparent and accessible for people who need finance to get on the road. We work closely with dealers, brokers and customers to make sure that every application, decision and interaction is fast, fair and easy to understand. Because we’re a small, high-performing team, everyone has real ownership. We combine hands-on operations with a strong focus on automation and technology. We’re designing highly automated, AI-powered processes that let us move faster and smarter than traditional lenders. The Role We're hiring a Data Scientist to sit at the heart of how we lend: who we say yes to, at what price, and how we know it's working. Our customers are people that traditional lenders struggle to assess. Many are new to the UK, have thin or no credit files, and don't fit neatly into off-the-shelf bureau scores. That makes credit decisioning at Marshmallow a genuinely hard, genuinely interesting problem: we combine bureau data, Open Banking, insurance, application and behavioural data to build a view of risk that others can't, and we need to do it in a way that is fair, explainable and compliant. This role sits between a traditional credit analyst and a data scientist. You'll build and monitor scorecards, design and test credit strategies, dig into portfolio performance to find out what's really going on, and turn large, messy datasets into insights that change how we lend. You'll own your work end-to-end: from framing the question and pulling the data through to modelling, presenting a recommendation and seeing it live in our decision engine. You'll be working with a small team and a modern stack, alongside a Head of Credit who has built this function from scratch and who will give you real ownership from day one. This is not a role where you hand models over a wall and move on - you'll see the impact of your decisions immediately.   What you'll be doing • Build, validate and monitor application and behavioural scorecards, using bureau, Open Banking and internal data to improve how we assess new-to-UK and thin-file customers. • Design, test and refine our credit strategy: cut-offs, affordability rules, pricing tiers and limits, with a clear view of the trade-off between risk, volume and margin. • Run experiments and champion/challenge tests to prove that changes to policy and models actually work before we scale them. • Explore new data sources and alternative signals, and build the case for using (or not using) them in decisioning. •

View the official posting →