Senior Data Scientist (Fraud Detection and Investigative Analytics)

Node.Digital•Washington, DC

6d•Remote

About The Position

This role focuses on Fraud Detection and Investigative Analytics, requiring expertise in developing and implementing advanced statistical and machine learning models to combat financial fraud, improper payments, and non-compliance within SBA programs. The position involves close collaboration with criminal investigators, adherence to federal rules, and the creation of data-driven insights for investigations and leadership.

Requirements

Master's, Ph.D., or doctorate level equivalent degree in data science, machine learning, computer science, mathematics, or a related field, OR ten years of applied work experience in these fields.
5+ years of experience designing, implementing, and maintaining advanced AI systems and predictive models.
5+ years of experience developing analytic rules and models using leading edge analytic tools and best practices.
5+ years of experience developing regression, classification, and other statistical models to identify anomalies, patterns, and predictive variables.
3+ years of experience providing data support for criminal investigations into financial fraud or abuse of government funds.
3+ years of experience manipulating data in Python (Pandas required).
3+ years of experience working in a modern cloud environment (Azure, AWS, or GCP).
2+ years of experience conducting advanced data analysis in SQL (SQL Server and PostgreSQL).
2+ years of experience developing and scaling natural language processing solutions.
2+ years of experience presenting methods and findings to technical and non-technical stakeholders, both orally and in written products and visualizations.
Public Trust Clearance

Nice To Haves

Cloud certification in Azure, AWS, or GCP.
Direct experience with SBA loan programs (7(a), 504, EIDL, or PPP), or with comparable federal lending or grant fraud.
Entity resolution, record linkage, or graph and network analysis applied to fraud.
Experience producing analytic products used in a criminal referral or prosecution.
Model explainability practice such as SHAP or comparable feature attribution methods.

Responsibilities

Review, maintain, and extend existing loan fraud indicators.
Design, develop, test, calibrate, and implement advanced statistical and machine learning models targeting financial fraud, improper payments, and non-compliance.
Build and refine supervised and unsupervised models (regression, Bayesian, clustering, ensemble approaches).
Perform data quality analysis on source tables.
Develop repeatable processes for combining and analyzing large relational, structured, and unstructured data sources.
Collaborate with criminal investigators to determine and execute analytic strategies for fraud cases.
Adapt analysis as case needs shift and proactively surface data quality issues.
Adhere to federal rules of criminal procedure governing protected information.
Develop case leads for SBA OIG investigations from model outcomes.
Document all methodology, test models, and production models to satisfy evidentiary requirements.
Build visualizations and dashboards to convey methodological choices, outcomes, and predictive capability.
Deliver findings in multiple registers: data summaries and visualizations for investigative staff, executive summaries for OIG leadership.
Coordinate with data engineering for efficient machine learning architecture.
Create programming and automation techniques to improve task efficiency.
Identify new business questions to expand the scope of analysis and reporting.