• Evaluation design and execution. Design and run rigorous analyses (including coverage rates, incremental lift, etc.) for new external data sources across bureau, open banking, and alternative data categories. Define the right population, baseline, methodology, and success criteria for each evaluation in partnership with the strategy team before analysis begins.
• Incremental value measurement. Measure the marginal contribution of each data source over Client's existing data signals. Champion-challenger testing, population swap analysis, and coverage gap quantification are core tools.
• Retrospective analytics. Build and maintain the analytical framework that tracks post-integration performance for every data source in the portfolio. At six and twelve months post-launch, answer the question: did this source deliver the lift the evaluation projected, and does it continue to clear the performance threshold that justifies its cost?
• Coverage and population analysis. Quantify where external data gaps are limiting Client's ability to serve specific populations (i.e. thin file, new-to-Client, underserved segments) and model the incremental approval and loss impact of closing those gaps.

• Evaluation design and execution. Design and run rigorous analyses (including coverage rates, incremental lift, etc.) for new external data sources across bureau, open banking, and alternative data categories. Define the right population, baseline, methodology, and success criteria for each evaluation in partnership with the strategy team before analysis begins.
• Incremental value measurement. Measure the marginal contribution of each data source over Client's existing data signals. Champion-challenger testing, population swap analysis, and coverage gap quantification are core tools.
• Retrospective analytics. Build and maintain the analytical framework that tracks post-integration performance for every data source in the portfolio. At six and twelve months post-launch, answer the question: did this source deliver the lift the evaluation projected, and does it continue to clear the performance threshold that justifies its cost?
• Coverage and population analysis. Quantify where external data gaps are limiting Client's ability to serve specific populations (i.e. thin file, new-to-Client, underserved segments) and model the incremental approval and loss impact of closing those gaps.

• Must Have
• 3+ years of experience in data science, quantitative analytics, or credit risk modeling in financial services or fintech
• Strong proficiency in Python and SQL to build, run, and document end-to-end analytical workflows independently
• Hands-on experience building and evaluating machine learning models, including model validation and performance benchmarking
• Demonstrated experience measuring incremental lift or marginal contribution in a credit or risk marketing context
• Familiarity with credit risk concepts such as bureau data, score distributions, population segmentation, approval rate and loss rate tradeoffs
• Strong verbal and written communication skills to clearly communicate analytical results to a non-technical audience
• Comfort operating with ambiguity where many of the data sources you will evaluate will be new to client
•  
• Nice to Have
• Experience evaluating or working with credit bureau data (Transunion, Equifax, Experian, CRIF, Schufa, etc.)
• Experience evaluating or working with open banking data (Plaid, Tink,  Finicity, etc.)
• Exposure to international credit markets across UK, Germany, Spain, France, and other EU countries
• Familiarity with vendor economics or unit cost analysis
• Experience working with analytical sandbox environments
• Graduate degree in statistics, economics, computer science, or a related quantitative field