Quantitative Model Analyst in Minneapolis, Minnesota

U.S. Bank • Minneapolis, MN

2d • Hybrid

About The Position

U.S. Bank is seeking the position of Quantitative Model Analyst in Minneapolis, Minnesota. Essential Responsibilities: The Quantitative Model Analyst will collaborate with model owners and external vendors to validate machine learning fraud models in compliance with OCC 2011-12 Regulatory Guidance and U.S. Bank’s Model Risk Management Policy and Standards. The position is responsible for performing comprehensive independent validations of both proprietary vendor and custom-built fraud models using statistical and machine learning techniques such as logistic regression and XGBoost. Duties include reviewing and validating model documentation related to development, implementation, and monitoring processes to ensure accuracy, completeness, and regulatory compliance. The role also involves developing independent statistical models to challenge conceptual frameworks, methodologies, data selection, model performance, and outcome analysis. The incumbent prepares detailed written validation reports and presents findings to model owners, key stakeholders, regulators, and senior management. They identify and recommend corrective actions to address model performance risks and documentation deficiencies, ensuring timely remediation. Additionally, the position coordinates quarterly monitoring reviews of fraud model monitoring reports, identifying emerging trends and potential deficiencies to proactively mitigate risks. The incumbent tracks monitoring outcomes across model ownership groups and communicates findings and clarifications to model owners as needed. The role also includes updating and maintaining the Fraud Model Training Guide to keep information current for new team members, as well as managing the internal fraud research library to improve validation efficiency and provide standardized statistical interpretations for commonly used methodologies. Position may allow working from home within a commuting distance of worksite location. Multiple Positions.

Requirements

• Requires a Master’s degree in Statistics or Mathematics plus 2 years of experience developing, validating, and implementing predictive models.
• Will accept a Bachelor’s degree in Statistics or Mathematics plus 5 years of experience developing, validating, and implementing predictive models in lieu of a Master’s degree plus 2 years of experience.
• Must possess 2 years of experience with Master’s or 5 years of experience with Bachelor’s with all of the following: developing predictive models using statistical and machine learning techniques, including logistic regression, decision trees, gradient boosting (XGBoost), and clustering, to generate actionable business insights; experience in target variable analysis, algorithm selection, hyperparameter tuning, reject inference, stress testing, and bootstrapping for predictive model development and optimization; applying risk modeling techniques to segment data; validating and implementing predictive models designed to assess the probability of default to ensure accuracy, reliability, and scalability; extracting historical data and performing data validation to ensure accuracy of information; utilizing programming languages and tools including R, Python, SAS, and SQL to extract, clean, transform, and perform quality assurance on large datasets; combining large-scale datasets for analysis; creating and maintaining automated modeling pipelines, dashboards, and reporting tools to support data-driven decision-making; collaborating with cross-functional teams to translate business requirements into quantitative solutions; and documenting methodologies and presenting findings clearly to both technical and non-technical stakeholders.

Responsibilities

• Collaborate with model owners and external vendors to validate machine learning fraud models in compliance with OCC 2011-12 Regulatory Guidance and U.S. Bank’s Model Risk Management Policy and Standards.
• Perform comprehensive independent validations of both proprietary vendor and custom-built fraud models using statistical and machine learning techniques such as logistic regression and XGBoost.
• Review and validate model documentation related to development, implementation, and monitoring processes to ensure accuracy, completeness, and regulatory compliance.
• Develop independent statistical models to challenge conceptual frameworks, methodologies, data selection, model performance, and outcome analysis.
• Prepare detailed written validation reports and presents findings to model owners, key stakeholders, regulators, and senior management.
• Identify and recommend corrective actions to address model performance risks and documentation deficiencies, ensuring timely remediation.
• Coordinate quarterly monitoring reviews of fraud model monitoring reports, identifying emerging trends and potential deficiencies to proactively mitigate risks.
• Track monitoring outcomes across model ownership groups and communicates findings and clarifications to model owners as needed.
• Update and maintain the Fraud Model Training Guide to keep information current for new team members.
• Manage the internal fraud research library to improve validation efficiency and provide standardized statistical interpretations for commonly used methodologies.

Benefits

• Healthcare (medical, dental, vision)
• Basic term and optional term life insurance
• Short-term and long-term disability
• Pregnancy disability and parental leave
• 401(k) and employer-funded retirement plan
• Paid vacation (from two to five weeks depending on salary grade and tenure)
• Up to 11 paid holiday opportunities
• Adoption assistance
• Sick and Safe Leave accruals of one hour for every 30 worked, up to 80 hours per calendar year unless otherwise provided by law

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees