Modeling - Risk Modeler I

About the role

This position is part of the Risk Management department. Risk professionals identify revenue opportunities and risk trends by monitoring the performance of the existing portfolio, growth opportunities, and general market trends. The team develops and implements strategies for credit line increases, authorizations, collection, fraud, retention, and the sale of revenue-based products. The Risk Modeler I supports the development, implementation, monitoring, and maintenance of consumer credit risk and decision models within Risk Management. The role focuses on individual borrowers and credit card accounts, including customer acquisition, underwriting, credit line management, and collections. Working under the guidance of experienced modelers, the employee completes defined analytical tasks and builds statistical modeling, consumer-credit, and model-governance capabilities.

Responsibilities

• Support development of application and behavioral risk models and related consumer decision models.
• Fit machine learning and benchmark models and assist with challenger models development under technical guidance.
• Extract and join consumer application, credit bureau, account, payment, and transaction data using SQL and Python/PySpark.
• Reconcile record counts, investigate missing or inconsistent values, and document data assumptions.
• Perform exploratory, univariate, and bivariate analysis; support feature engineering and segmentation using attributes such as utilization, balances, repayment behavior, and credit history.
• Apply established sampling, observation and performance windows, and train/test or out-of-time splits.
• Identify potential data leakage and escalate unexpected results.
• Calculate and interpret model-performance measures, including KS, ROC/AUC, lift, population stability, and calibration, with guidance on business interpretation.
• Execute periodic monitoring and analyze changes in score distributions, delinquency, default, and charge-off performance.
• Support portfolio and vintage analysis and investigate material changes.
• Perform analytical QA and coding checks; maintain reproducible code, data definitions, and records of development decisions.
• Prepare analytical exhibits and assigned sections of model-development documentation.
• Support responses to independent Validation and Model Risk Management questions.
• Partner with Model Operations and Technology to support implementation testing, reconcile development and production scores, and document discrepancies.
• Communicate findings, assumptions, limitations, and progress clearly to modelers and business partners; escalate data issues and delivery risks promptly.
• Follow established data-security, coding, and model-governance procedures.
• Support model explanations and reason-code analysis where applicable under guidance from senior modelers and Compliance.
• Perform other related duties as assigned.

Requirements

• Bachelor’s degree in a quantitative discipline such as Statistics, Mathematics, Applied Mathematics, Data Science, Computer Science, Economics, Financial Engineering, Quantitative Finance, Operations Research, Industrial Engineering, or Business Analytics.
• 2+ years of relevant modeling or quantitative analytics experience. Internships, research, and substantive academic projects may demonstrate the required skills.
• Working proficiency in Python/PySpark, demonstrated through practical data preparation, analysis, and reproducible coding.
• Ability to learn the team’s modeling tools.
• Basic understanding of predictive modeling, training and evaluation datasets, overfitting, and model-performance measures such as ROC/AUC and KS.
• Ability to identify data inconsistencies, question unexpected results, and document analytical assumptions and limitations.
• Clear written and verbal communication, attention to detail, and ability to complete defined deliverables under guidance.

Preferred qualifications

• Experience or project exposure in consumer lending, credit card issuing, or consumer credit bureau data.
• Hands-on exposure to machine-learning methods such as gradient boosting/XGBoost or model-explainability techniques.
• Experience with Git or another version-control tool and reusable analytical workflows.
• Exposure to Snowflake, BigQuery, or another cloud analytical environment.
• Exposure to model monitoring, implementation testing, or model-development documentation.
• Master’s degree in a quantitative discipline such as Statistics, Mathematics, Applied Mathematics, Data Science, Computer Science, Economics, Financial Engineering, Quantitative Finance, Operations Research, Industrial Engineering, or Business Analytics.

About Credit One Bank

Credit One Bank, N.A. is a data-driven financial services company based in Las Vegas. Founded in 1984, Credit One Bank offers a spectrum of credit card products for people in all stages of financial life.