Head of Data Science, Credit Risk Analytics

Cleo

22h

About The Position

Cleo is hiring a Head of Data Science to lead credit performance measurement and monitoring within its Risk & Payments pillar. This is a player-coach position, combining hands-on analysis with managing Credit Data Scientists and Analysts, setting direction, developing team members, and owning the function’s output. The role owns the frameworks and metrics used to monitor credit products and leads analyses that explain performance changes and inform action. The position is part of a Credit Policy and Analytics function focused on portfolio performance and on building and growing responsible Earned Wage Access (EWA) and Pay Later products that can scale across markets while protecting users from high-cost debt. The role partners with Risk Modelling, Credit Policy, Decision Science, Product, Risk, and Leadership.

Requirements

Strong SQL and Python skills, with the ability to work directly from the data warehouse.
Track record of owning analyses end-to-end, from framing the question to delivering a recommended change.
Hands-on experience with predictive models in credit, fraud, or a similar area.
Fluency in AUC/Gini, calibration, PSI/CSI, and drift.
Fluency in credit portfolio metrics, including arrears buckets, roll rates, loss rate, yield, and marginal loss, and understanding how they connect to unit economics.
Experience directly managing analysts or data scientists, including prioritization, performance management, and people development.

Nice To Haves

Experience with short-term or revolving credit products.
Experience with both UK and US regulatory frameworks.

Responsibilities

Design and maintain the credit risk metric framework, including arrears, default, yield, loan-to-value (LTV), and marginal loss metrics, along with dashboards and alerts for identifying arrears spikes, roll-rate changes, and decisioning anomalies.
Partner with Risk Modelling to translate model metrics such as AUC, PSI, calibration, and drift into policy and product recommendations, and diagnose whether performance changes are model-driven, macroeconomic, or operational.
Lead end-to-end root-cause investigations, from framing the question through analysis and recommendation, on issues such as arrears spikes and yield compression.
Use driver analysis, including SHAP, feature importance, and decomposition, and present findings to Risk, Product, and Leadership.
Work with Credit Policy and Decision Science to build evaluation frameworks for policy changes and quantify their marginal impact.
Support elasticity and profitability modelling for pricing and credit limits.
Directly manage Credit Data Scientists and Analysts, setting priorities, managing performance, and developing team members.
Balance hands-on analysis with leading the team and owning the function’s output.