Senior Data Modeler, Fraud Risk Detection

Summary

Experian is a global data and technology company that powers opportunities for people and businesses. The Senior Data Modeler will help develop fraud detection models and features, investigate fraud patterns, evaluate machine learning models, and support production deployment. The role also involves collaborating with data scientists and engineers, monitoring models, communicating findings, and applying standards for privacy, explainability, validation, and governance.

Responsibilities

• Explore complex datasets, with guidance from senior team members, to identify fraud patterns, attack methods, and behavioral signals
• Work with senior data scientists to translate fraud questions into testable hypotheses
• Help build machine learning models for fraud detection across account opening, account takeover, and identity risk
• Evaluate models using both technical and business metrics, such as precision, recall, fraud capture rate, false-positive rate, and customer friction
• Develop and validate features using identity, transactional, behavioral, and other available data sources
• Write clean, well-tested code, and work with engineering to bring models and features into production
• Partner with the score monitoring team to help set up model and feature monitoring, and support research on related client questions
• Help prepare analyses and communicate findings to both technical and nontechnical audiences
• Apply Experian's standards for data privacy, model documentation, explainability, validation, and governance

Skills

• 1+ years of experience in data science, machine learning, statistical modeling, or a related quantitative field
• Bachelor's or advanced degree in computer science, statistics, mathematics, economics, engineering, data science, or another quantitative discipline
• Foundation in supervised learning, model evaluation, feature selection, statistical inference, and techniques such as classification and anomaly detection
• Proficiency in Python, with the ability to write clean, readable, and well-tested code
• Familiarity with common data science and machine-learning tools such as pandas, NumPy, and scikit-learn
• Investigative mindset and the ability to move from unusual data patterns to testable hypotheses
• Familiarity with PySpark, cloud platforms such as Amazon Web Services, Google Cloud, Azure, Databricks, and Snowflake, or other large-scale data tools
• Exposure to financial services, FinTech, payments, or another regulated or fraud-intensive industry, through coursework, internship, or prior work

Qualifications

Must Haves

• 1+ years of experience in data science, machine learning, statistical modeling, or a related quantitative field
• Bachelor's or advanced degree in computer science, statistics, mathematics, economics, engineering, data science, or another quantitative discipline
• Foundation in supervised learning, model evaluation, feature selection, statistical inference, and techniques such as classification and anomaly detection
• Proficiency in Python, with the ability to write clean, readable, and well-tested code
• Familiarity with common data science and machine-learning tools such as pandas, NumPy, and scikit-learn
• Investigative mindset and the ability to move from unusual data patterns to testable hypotheses
• Familiarity with PySpark, cloud platforms such as Amazon Web Services, Google Cloud, Azure, Databricks, and Snowflake, or other large-scale data tools
• Exposure to financial services, FinTech, payments, or another regulated or fraud-intensive industry, through coursework, internship, or prior work

Benefits

• Bonus plan
• Medical, dental, and vision benefits
• Matching 401K
• Flexible work environment, with the ability to work remote, hybrid, or in-office
• Flexible time off including volunteer time off, vacation, sick leave, and 12 paid holidays
• Variable pay opportunity
• Comprehensive benefits package