Principal Associate, Data Scientist, SBB Fraud

As a Principal Associate Data Scientist for SBB Fraud, you will build and deploy machine learning models to detect and prevent small business fraud. You will leverage Python, Conda, AWS, H2O, and Spark to develop models through design, training, evaluation, validation, and implementation, partnering with cross-functional teams to deliver fraud defenses customers can rely on.

• Partner with cross-functional teams of data scientists, software engineers, and product managers
• Leverage Python, Conda, AWS, H2O, and Spark to extract insights from large numeric and textual datasets
• Build machine learning models through design, training, evaluation, validation, and implementation
• Translate modeling complexity into tangible fraud prevention business goals
• Develop fraud models that protect customers and Capital One against transaction, account opening, and account takeover fraud

Fraud-focused data science role using Python with cloud platforms such as AWS. You will develop statistical and machine learning models including clustering, classification, sentiment analysis, time series, and deep learning, using H2O and Spark and validating performance via confusion matrix and ROC curve metrics.

The ideal candidate is a Principal Associate Data Scientist specializing in fraud modeling with strong statistical modeling experience. They have hands-on machine learning development using Python and cloud platforms such as Amazon Web Services, with practical tool experience including H2O and Spark. They can build and validate models through design, training, evaluation, validation, and implementation, and communicate modeling results into actionable business outcomes for SBB fraud prevention.