Since 2018, the head of risk has built his team to include a Deputy Chief Risk Officer and an analyst. We helped hire the Deputy Chief Risk Officer three years ago. The next iteration could involve you.
As you know, the risk models depend on perfect data. That's the goal of this position - to bring data perfection from 90% to 100% and to do much more.
Because of the importance of this position, you will be part of the risk department and therefore part of a business function that reports to the President. You'll learn from the best and bolt on business rule knowledge to your data engineering expertise.
Position Summary
The Data Scientist will be responsible for developing, implementing, and maintaining advanced analytical and predictive models that support credit risk management, loan origination, portfolio performance, collections, and profitability.
This position will work closely with Credit Risk, Operations, Finance, IT, and senior management to transform large volumes of loan and customer data into actionable insights. The ideal candidate combines strong statistical and machine-learning expertise with an understanding of consumer lending and the ability to translate complex analytical results into practical business recommendations.
Key Responsibilities
Credit Risk & Predictive Modeling
Develop, validate, and monitor predictive models related to credit risk, loan performance, delinquency, charge-offs, and recoveries.
Develop models to predict probability of default, loss severity, prepayment, roll rates, and customer payment behavior.
Analyze borrower, loan, geographic, product, and vintage characteristics to identify drivers of portfolio performance.
Develop segmentation strategies to identify differences in credit risk and profitability across customer and loan populations.
Evaluate model performance using appropriate statistical and machine-learning techniques.
Continuously monitor model performance and recommend adjustments as portfolio characteristics and economic conditions change.
Loan Origination & Underwriting
Analyze historical loan performance to identify characteristics associated with successful and unsuccessful loans.
Develop predictive tools and strategies that support underwriting and credit decisioning.
Evaluate the impact of underwriting policies, pricing, loan terms, and approval strategies on portfolio performance.
Partner with Credit Risk and Operations to identify opportunities to improve approval rates while appropriately managing credit risk.
Portfolio Performance
Develop analytical frameworks for monitoring loan performance by origination vintage, product, branch, geography, customer segment, and other relevant characteristics.
Identify emerging trends in delinquency, losses, payment behavior, and portfolio profitability.
Perform deep-dive analyses to determine the underlying causes of changes in portfolio performance.
Develop early-warning indicators to identify deteriorating portfolio segments.
Support forecasting of delinquency, losses, charge-offs, and recoveries.
Collections & Customer Behavior
Develop predictive models to improve collection strategies and prioritize accounts based on expected outcomes.
Analyze payment behavior and customer characteristics to identify opportunities for improved collection effectiveness.
Evaluate treatment strategies and measure the financial impact of collection initiatives.
Develop models to identify customers with potential for successful rehabilitation or repeat borrowing.
Data & Analytics
Work with large and complex datasets containing loan, customer, payment, credit, and operational information.
Develop efficient SQL queries and data pipelines to prepare data for analysis and modeling.
Establish reliable data definitions, analytical datasets, and performance metrics.
Identify data-quality issues and work with IT and business stakeholders to resolve them.
Develop automated reporting and analytical tools that allow management to monitor key portfolio trends.
Business Strategy
Translate analytical findings into clear recommendations for senior management.
Quantify the expected financial impact of proposed credit, underwriting, pricing, and collection strategies.
Support strategic initiatives through scenario analysis, forecasting, and predictive analytics.
Present analytical findings to both technical and non-technical audiences.
Partner with business leaders to identify opportunities where advanced analytics can improve profitability and reduce risk.
Required Qualifications
Bachelor's degree in Data Science, Statistics, Mathematics, Computer Science, Economics, Finance, or a related quantitative field.
3+ years of experience in data science, predictive analytics, statistical modeling, or a related field.
Strong SQL skills and experience working with large relational databases.
Strong knowledge of statistical modeling and machine-learning techniques.
Experience with Python, R, SAS, or similar analytical programming languages.
Experience with data visualization and communicating analytical results to business stakeholders.
Strong understanding of statistical concepts, model validation, and performance measurement.
Ability to independently translate business problems into analytical solutions.
Preferred Qualifications
Experience in consumer finance, installment lending, auto lending, credit cards, mortgage, or another lending environment.
Experience developing credit-risk or loan-performance models.
Experience with credit bureau data and/or alternative credit data.
Experience with XGBoost, gradient boosting, random forests, logistic regression, or other predictive modeling techniques.
Experience with model monitoring and model governance.
Knowledge of loan loss forecasting, reserves, charge-offs, delinquency, roll rates, and vintage analysis.
Experience with Power BI, Tableau, Power Pivot, or similar business intelligence tools.
Master's degree in Data Science, Statistics, Mathematics, Computer Science, Economics, or a related field.
Key Performance Indicators
Success in this role will be measured by the ability to:
Improve the company's ability to predict loan performance and credit risk.
Identify actionable opportunities to improve portfolio profitability.
Improve underwriting and credit decision strategies.
Reduce unexpected delinquency and credit losses.
Improve collection effectiveness.
Increase the speed and accuracy of portfolio analysis.
Develop reliable, scalable analytical models and reporting.
Provide management with clear, data-driven recommendations.
Core Competencies
Analytical and critical thinking
Statistical and predictive modeling
Credit-risk analysis
SQL and data management
Machine learning
Business acumen
Problem solving
Communication and presentation
Attention to detail
Ability to translate complex analysis into actionable business decisions
Reporting Relationship
The Data Scientist will report to the Chief Risk Officer or other designated senior leader and will work cross-functionally with Credit Risk, Finance, Operations, IT, and executive management.