Lead Analyst - Decision Science in Bradford

Contract Type: Permanent

Location: Bradford, Chatham, Petersfield or London

Working Pattern: Hybrid (usually a couple of days a week in the office). We welcome part-time and flexible arrangements and will aim to match your current flexibility where possible.

What We Offer

• Holidays: 25 days (rising to 30) + buy/sell up to 5 days + swap up to 4 bank holidays.
• Pension: Up to 10% employer contribution.
• Enhanced Leave: Enhanced maternity (post-probation), 4 weeks’ paternity, and paid neonatal & carers leave.
• Workations: Work abroad for up to 20 days a year in approved countries.
• Birthday Leave: Your birthday off—paid.
• Volunteering: 2 paid volunteering days.
• Learning: Access to Learning for all colleagues.
• Financial Wellbeing: Free Snoop Premium subscription.
• Healthcare: Self-pay Denplan & optional Private Medical Insurance.

The Role

As a Lead Analyst – Decision Science, you will play a key role in delivering innovative, accurate, and scalable models that underpin our collections and fraud strategies that support sustainable customer outcomes.

You and your Team

The Data & Analytics function is a centre of excellence that provides high-impact analytical expertise across the Vanquis Banking Group. We’re responsible for business-critical modelling, data innovation, credit bureau strategy, and actionable insights that drive customer and commercial outcomes. This new role will sit in our Decision Science team. The wider team focuses on developing robust, regulatory-aligned models and decisioning tools, and you will be specifically involved in developing and maintaining predictive models that enhance collections strategies and fraud detection frameworks.

As a Lead Analyst, you will:

• Lead and manage projects focused on developing predictive models and other tools for collections optimisation and fraud detection across Cards and Asset Finance portfolios.
• Assess customer behaviours, repayment patterns, and fraud trends, identifying opportunities to improve collections strategies and fraud prevention measures.
• Research and development of incorporating self-learning solutions.
• Work closely with Collections, Fraud, Risk, and Finance teams to translate analytical insights into actionable business strategies.
• Mentoring junior analysts, supporting skill development and contributing to a culture of continuous improvement.

What We’re Looking For

We’re looking for someone with a passion for data-driven decisioning and a track record of delivering operational, credit risk, and other predictive models in a regulated environment. You should enjoy combining technical excellence with commercial thinking and collaboration, while also being a pragmatic problem solver.

Essential skills and experience:

• 5+ years’ experience developing credit scorecards and other classification models within financial services.
• Proficiency in Python (Pandas, NumPy, Scikit-learn, Statsmodels, Matplotlib) for analysis, modelling, and visualisation.
• Strong theoretical knowledge of algorithms such as regression, tree-based methods (e.g. random forests, gradient boosting), and neural networks.
• Proficiency in SQL and experience with data extraction, manipulation, and analysis from relational databases.
• Solid understanding of statistical methods, experiment design, and hypothesis testing.
• Familiarity with Credit Reference Agency data, characteristics, and score usage.
• Demonstrated ability to explore and utilise unconventional data sources to drive analytical innovation.

Desirable skills:

• Excellent communication and stakeholder management skills, with the ability to influence non-technical audiences.
• Knowledge of model governance and regulatory standards (e.g. IFRS9, PRA expectations).
• Exposure to cloud-based analytics environments.
• Experience with machine learning techniques for fraud detection.
• Experience with optimisation techniques (linear programming, heuristics, simulation).

Offers are subject to standard background checks (credit, fraud and employment references).