Graph Data Scientist (Fraud Analytics & Investigative Support)

About the role

Praescient Analytics is seeking an experienced Graph Data Scientist to develop advanced graph analytics that uncover hidden relationships, organized fraud networks, synthetic identities, and other complex patterns supporting federal fraud detection and investigative missions.

Responsibilities

• Design, develop, and maintain graph-based analytic solutions supporting fraud detection, investigative analysis, and program integrity initiatives.
• Build and optimize graph databases, graph schemas, and knowledge graphs using Neo4j or comparable graph database technologies.
• Develop graph queries using Cypher or similar graph query languages to identify hidden relationships, fraud rings, suspicious networks, synthetic identities, and other complex entity relationships.
• Apply graph algorithms, statistical analysis, and machine learning techniques to identify emerging fraud patterns and anomalous network behavior.
• Design graph data models and scalable graph data pipelines that integrate structured and unstructured data from multiple public, non-public, commercial, and law enforcement data sources.
• Perform network analysis utilizing centrality measures, community detection, shortest path algorithms, clustering, and graph-based anomaly detection techniques.
• Collaborate with Data Engineers, Data Scientists, Investigative Analysts, and Technical Analytics Managers to integrate graph analytics into broader fraud detection models.
• Validate graph analytic outputs, document methodologies, and ensure graph models are accurate, explainable, and reproducible.
• Develop visualizations and relationship analyses that support investigative lead generation, case development, and executive briefings.
• Support continuous improvement of graph analytics capabilities through experimentation with emerging graph technologies, graph machine learning techniques, and knowledge graph methodologies.

Requirements

• Must have experience with Fraud Analysis
• Three (3) or more years of hands-on experience developing graph analytics using Neo4j or a comparable graph database platform.
• Demonstrated fluency in Cypher or a comparable graph query language.
• Strong understanding of graph theory and network analytics, including network topology, centrality measures, community detection, shortest path algorithms, graph clustering, and graph traversal techniques.
• Three (3) or more years of hands-on experience applying statistical analysis, machine learning, clustering, classifiers, and anomaly detection techniques to graph-structured data.
• Three (3) or more years of experience applying graph methods to fraud detection, relationship discovery, link analysis, and knowledge graph development.
• Experience designing graph data models, graph schemas, and graph data pipelines supporting large-scale, high-complexity datasets.
• Strong Python programming skills utilizing standard machine learning libraries and data science frameworks.
• Excellent written and verbal communication skills with the ability to explain complex technical concepts to both technical and non-technical audiences.

Preferred Qualifications

• Demonstrated experience in one or more of the following areas: Applying graph analytics to fraud detection, fraud prevention, financial crime investigations, program integrity, anti-money laundering (AML), or other complex investigative environments.
• Building knowledge graphs that integrate multiple public, non-public, commercial, financial, and law enforcement data sources into unified entity networks.
• Detecting organized fraud rings, synthetic identities, shell companies, nominee entities, shared addresses, common bank accounts, related businesses, and other non-obvious relationships through graph analytics.
• Designing and optimizing graph data pipelines, graph schemas, graph indexing strategies, and graph performance for enterprise-scale analytics environments.
• Applying graph data science algorithms including PageRank, Louvain community detection, connected components, similarity algorithms, node embeddings, graph embeddings, link prediction, and graph-based anomaly detection.
• Leveraging Python libraries such as NetworkX, Neo4j Graph Data Science (GDS), Pandas, Scikit-learn, PyTorch Geometric, or comparable graph analytics and machine learning frameworks.
• Supporting Offices of Inspector General (OIGs), law enforcement organizations, intelligence organizations, financial crime investigations, or other government oversight missions.
• Developing interactive graph visualizations, relationship maps, and investigative link analysis products that accelerate lead generation, case development, and investigative decision-making.