Risk Analyst – Data Science & Analytics

We are looking for a Risk Analyst – Data Science & Analytics to join our Analytics Product & Innovation team. This is a hands-on analytics role focused on developing and enhancing data-driven products using consumer bureau data, statistical techniques and machine learning. You will work from use-case exploration and analytical prototyping through validation, UAT and productisation support. The role is suited to someone who enjoys working directly with data and code, can build robust analytical solutions, and wants to see those solutions become repeatable products used by clients. Strong analytics and coding capability are more important than prior experience in any one risk domain. What you'll do Analyse large and complex bureau and financial-services datasets to identify patterns, signals and opportunities for new or enhanced analytics products. Translate a product idea or industry use case into a structured analytical approach, prototype and measurable success criteria. Build and benchmark statistical and machine-learning models, scores, segmentations, features and decision-support components appropriate to the use case. Perform data preparation, exploratory analysis, feature engineering, variable selection and analytical dataset creation using efficient Python and SQL code. Apply robust validation to assess predictive performance, stability, interpretability and business suitability; document assumptions and limitations clearly. Create reusable analytical code, utilities and automated workflows that can support repeatable product development rather than one-off analysis. Partner with Product and Technology teams on analytical requirements, UAT, defect investigation and productisation of new or enhanced capabilities. Support performance reviews of existing analytics products and identify opportunities for efficiency, feature enhancement or methodology improvement. Prepare clear analytical documentation and explain methodologies, results and product value to internal stakeholders and, where required, clients. Follow applicable data-security, model-governance, documentation and compliance standards. What success looks like High-quality, analytical prototypes and product enhancements that meet agreed acceptance criteria. Demonstrable improvement in product performance, usability or analytical coverage where an enhancement is made. Reusable, well-documented code and analytical assets that reduce repeated effort and support scale. Effective UAT support, low analytical defect leakage and strong documentation / governance discipline.

What you'll need to bring Approximately 3+ years of experience in analytics, data science, decision science, statistical modelling or a closely related field. Strong hands-on proficiency in Python for data manipulation, exploratory analysis, statistical modelling and machine learning. Strong working knowledge of SQL, including the ability to extract, transform and analyse large and complex datasets. Sound grounding in applied statistics, including sampling, distributions, hypothesis testing, regression and model evaluation. Hands-on experience with common supervised and unsupervised techniques such as regression, tree-based methods, ensemble methods, gradient boosting, classification, clustering and segmentation. Understanding of model-development practices including train/validation/test design, cross-validation, overfitting, performance metrics, stability and interpretability. Strong data-wrangling, data-quality assessment, feature-engineering and analytical validation skills. Ability to convert a business question into a structured analytical approach and communicate findings clearly to technical and non-technical stakeholders. A disciplined approach to coding, documentation, reproducibility and quality assurance. Good to have SAS or another statistical programming environment. Git or similar version-control tools and collaborative coding practices such as peer review. Cloud analytics platforms, di