Senior Fraud Data Analyst - Commercial Fraud Operations Analytics Lead - Remote

UnitedHealth Group•Eden Prairie, MN

23h•$91,700 - $163,700•Remote

About The Position

Optum Financial prevents and responds to fraud to protect customers and the business. The Senior Fraud Data Analyst serves as the analytics workstream lead for Commercial Fraud Operations, supporting the Commercial Payments line of business. This role leverages advanced analytics, machine learning, and AI-enabled insights to support fraud monitoring, investigations, risk decisioning, and loss mitigation across Commercial Payments products and channels. In partnership with Commercial Fraud Operations, Product, Technology, and Risk stakeholders, the individual will define requirements, build scalable reporting and analytics solutions, evaluate fraud detection performance, and identify opportunities to improve operational effectiveness and fraud outcomes. "Lead" reflects ownership of analytics delivery, stakeholder alignment, and prioritization of workstreams rather than direct people management.

Requirements

5+ years of experience in fraud analytics, risk analytics, financial crime, payments analytics, business intelligence, or a related analytical function
5+ years of SQL with experience querying and analyzing large-scale datasets containing millions of records
3+ years of experience with analytics initiatives or cross-functional workstreams, including stakeholder management, prioritization, and delivery accountability
2+ years of experience developing analytics solutions using Python, R, SAS, or similar programming languages, with hands-on experience leveraging cloud-based analytics platforms such as MS Fabric, Databricks, Snowflake, Google Cloud Platform or Amazon RedShift
2+ years of experience building dashboards and reporting solutions using Power BI, Tableau, or comparable visualization platforms
Demonstrated experience applying statistical analysis, predictive modeling, machine learning, AI-enabled analytics, or anomaly detection techniques to solve business problems
Experience defining, monitoring, and improving operational KPIs, controls, and performance metrics
Experience translating analytical findings into operational recommendations, fraud detection improvements, control enhancements, or measurable risk reduction outcomes
Experience managing end-to-end analytics delivery, including requirements gathering, data validation, testing, implementation, and post-production monitoring

Nice To Haves

Professional certifications such as Certified Fraud Examiner (CFE), Certified Analytics Professional (CAP), Certified Financial Crime Specialist (CFCS), Azure Data Scientist Associate, Databricks certifications, or comparable analytics, fraud, or AI credentials
Experience partnering with Product, Engineering, and Data Science teams to deploy fraud analytics, machine learning models, or AI-enabled capabilities into production environments
Experience using generative AI tools to support coding activities, including drafting, reviewing, debugging, or improving SQL, Python, or related analytics code
Experience optimizing fraud detection strategy through rule mining, champion/challenger testing, segmentation analysis, and other optimization methodologies
Experience with generative AI, machine learning, natural language processing (NLP), or AI-assisted investigation tools in a fraud, risk, or operations environment
Experience supporting regulatory, audit, compliance, or risk governance reviews within a highly regulated industry
Experience with Commercial Payments products, including ACH, wire transfers, virtual cards, checks, and emerging payment channels
Demonstrated ability to operate effectively in ambiguous environments, establish structure where processes, reporting, or analytics capabilities do not yet exist, and influence stakeholders across operations, product, technology, and risk functions

Responsibilities

Lead intake, prioritization, sequencing, and delivery coordination for fraud analytics initiatives supporting Commercial Payments, managing multiple concurrent stakeholder requests and dependencies
Translate business objectives into measurable analytics deliverables, ensuring timely execution and adoption of solutions
Define business requirements and delivery priorities for scalable fraud analytics capabilities, partnering with Product, Technology, Data Science, and Fraud Operations stakeholders to deliver actionable fraud intelligence, performance insights, risk monitoring, and decision support across Commercial Payments
Partner with Commercial Fraud Operations, Product, and Technology teams to develop, evaluate, and optimize fraud detection strategies utilizing rules, predictive analytics, machine learning models, and AI-enabled monitoring capabilities
Evaluate model and rule performance using key measures such as precision, recall, false positive rates, fraud capture rates, and operational impact
Analyze large, complex datasets containing transaction, fraud case, operational, and customer data to identify emerging fraud trends, root causes, and control opportunities
Deliver actionable recommendations that reduce fraud losses, improve operational efficiency, and strengthen risk controls
Define requirements and support development of a commercial payments fraud intelligence repository or data product that consolidates information from multiple sources to build fraud profiles, identify emerging threats, and support fraud detection, prevention, investigation, reporting, and risk mitigation activities
Design and maintain enterprise dashboards and reporting solutions using tools such as Power BI or Tableau
Communicate analytics findings and business implications through executive-ready presentations, supporting operational, product, and risk management decisions
Support basic data architecture and engineering needs by building foundational reports, datasets, and pipelines that convert bronze medallion tables to silver and gold, creating the infrastructure needed for scalable reporting, dashboards, and advanced analytics
Develop and maintain automated analytics workflows using SQL, Python, AI-assisted analytics tools, or related technologies to improve reporting scalability and efficiency, including use of generative AI tools to write, review, and debug code where appropriate
Identify opportunities to leverage generative AI and advanced analytics capabilities to enhance fraud investigations, monitoring, and operational decision-making
Navigate complex organizational processes to obtain approvals for data access, usage, and governance initiatives
Establish and maintain standardized KPI definitions, metric libraries, data quality controls, and governance documentation
Ensure fraud analytics outputs are reproducible, audit-ready, and aligned with enterprise governance standards