USAA is seeking to reduce fraud losses and enhance the overall member experience by developing advanced machine learning models to detect and prevent fraud across various channels.
Requirements
- programming languages such as Python, R, or similar
- experience with querying and preprocessing data from structured and unstructured sources using SQL, NoSQL, or similar technologies
- familiarity with various data formats, including JSON, XML, and text files
- knowledge of classical supervised modeling techniques (linear/logistic regression, decision trees, support vector machines, etc.)
- knowledge of unsupervised learning methods (clustering algorithms, dimensionality reduction, etc.)
- experience with training and validating complex models
- ability to write clean, well-documented code
Responsibilities
- capturing, interpreting, and manipulating both structured and unstructured data to develop analytical solutions that address business challenges
- selecting appropriate modeling techniques based on data limitations and business requirements
- developing and deploying models within the Model Development Control (MDC) and Model Risk Management (MRM) frameworks
- ensuring compliance with regulatory standards
- creating comprehensive technical documentation to facilitate knowledge sharing and risk management
- translating business questions into analytical tasks, performing analyses, and presenting results clearly to non-technical colleagues
- collaborating with Data Engineering, IT, and business units to deploy solutions aligned with strategic goals
Other
- minimum of a bachelor’s degree in mathematics, computer science, statistics, economics, finance, actuarial sciences, or related fields
- at least two years of experience in predictive analytics or data analysis
- strong communication skills to effectively translate technical findings into actionable insights for non-technical stakeholders
- ability to work in a team environment and collaborate with cross-functional teams
- occasional travel for business purposes
