Lead Data Scientist, Fraud Detection Analytics at USAA Colorado Springs

Salary: $138, per year

• Bachelor’s degree in mathematics, computer science, statistics, economics, finance, actuarial sciences, science and engineering, or another similar quantitative discipline; OR 4 years of experience in statistics, mathematics, quantitative analytics, or related fields may substitute for the degree requirement.
• 6 years of experience in predictive analytics or data analysis.
• 4 years of experience in training and validating statistical, physical, machine learning, or other advanced analytics models.
• 4 years of experience using a dynamic scripting language (such as Python or R) for statistical analyses and/or developing and scoring AI/ML models.
• Proven track record of writing clear, well-documented code with necessary comments for logic transparency.
• Strong experience in querying and preprocessing data from structured and/or unstructured databases using languages such as SQL, HQL, No
  
  SQL, etc.
• Proficiency in handling structured, semi-structured, and unstructured data files (e.g., delimited numeric data, JSON/XML files, and text documents).
• Demonstrated ability in performing ad-hoc analytics using descriptive, diagnostic, and inferential statistics.
• Capability to assess and communicate the regulatory implications and expectations of specific modeling projects.
• Advanced knowledge of classical supervised modeling concepts for prediction (e.g., linear/logistic regression, discriminant analysis, support vector machines).
• Advanced expertise in unsupervised modeling techniques (e.g., k-means clustering, hierarchical clustering, neighbors algorithms).
• Experience in guiding and mentoring junior technical staff in business interactions and model development.
• Experience in communicating analytical results to non-technical business partners with a focus on actionable business recommendations.

• Gather, interpret, and manipulate both structured and unstructured data to enable advanced analytical solutions for the business.
• Develop scalable, automated solutions by employing machine learning, simulation, and optimization to deliver valuable business insights.
• Select appropriate modeling techniques considering data limitations, applications, and business needs.
• Create and implement models within the Model Development Control (MDC) and Model Risk Management (MRM) frameworks.
• Draft and assist peers in creating technical documents for knowledge preservation, risk management, and technical review purposes.
• Assess business needs to recommend analytical and modeling projects that can add value.
• Collaborate with business and analytics leaders to prioritize analytical and modeling challenges.
• Build and maintain a robust library of reusable, production-quality algorithms and supporting code to ensure transparency and the use of high-quality data in development and research efforts.
• Translate complex business requests into specific analytical questions, perform the analysis or modeling, and communicate outcomes to non-technical colleagues with a focus on actionable recommendations.
• Identify project breakthroughs, risks, and challenges that may impede project success or implementation.
• Develop best practices for engaging with Data Engineering and IT to deploy production-ready analytical assets in line with modeling best practices and model risk management standards.
• Stay updated on innovative techniques and actively seek learning opportunities to expand knowledge of new methodologies.
• Mentor junior data scientists in modeling, analytics, and computer science tasks.
• Participate in internal communities that promote the development and transformation of data science technologies and culture.
• Ensure risks associated with business activities are optimally identified, measured, supervised, and…