Senior Data Scientist (Fraud Detection and Investigative Analytics)

Senior Data Scientist (Fraud Detection and Investigative Analytics)

Location: Herndon, VA (Remote Work)

Must have an Public Trust Clearance

KEY RESPONSIBILITIES

• Review, maintain, and extend all existing loan fraud indicators developed by TSD, and provide authoritative expertise on analytic method selection.
• Design, develop, test, calibrate, and implement advanced statistical and machine learning models targeting financial fraud, improper payments, and non compliance within SBA programs.
• Build and refine both supervised and unsupervised models, including regression, Bayesian, clustering, and ensemble approaches, and tune candidate models to determine best fit.
• Perform data quality analysis on source tables to identify abnormalities and inconsistencies, and develop repeatable processes for combining and analyzing large relational, structured, and unstructured sources.
• Collaborate directly with criminal investigators to determine and execute analytic strategies supporting loan fraud cases, adapting analysis as case needs shift and proactively surfacing data quality issues.
• Adhere closely to the federal rules of criminal procedure governing protected information, including Rule 6(e).
• Develop case leads for SBA OIG investigations from model outcomes.
• Document all methodology, test models, and production models in a form that satisfies criminal evidentiary requirements.
• Build visualizations and dashboards that convey methodological choices, outcomes, and predictive capability, and iterate them on end user feedback.
• Deliver findings in multiple registers: data summaries and visualizations for investigative staff, executive summaries for OIG leadership.
• Coordinate with the data engineering seat so the architecture supports machine learning efficiently.
• Create programming and automation techniques that improve task efficiency using SharePoint, Python, Excel, Power BI, Power Apps, and similar tools.
• Identify new business questions that expa