Principal, Advanced Analytics – Internal Claims Fraud

Liberty Mutual Insurance•,

1d•$110,300 - $138,000

About The Position

We’re looking for an experienced, highly independent advanced analytics professional to join our Internal Claims Fraud Advanced Analytics team. In this stakeholder-focused role, you will analyze complex claims data to identify fraud signals, develop investigator-ready leads, and uncover fraud patterns that protect the company from financial loss. You will partner directly with the Claims Fraud Investigation team and cross-functional operational, data, technology, and analytics teams to turn ambiguous business problems into structured analyses and actionable recommendations. We are looking for someone who can independently determine the right analytical approach, distinguish signal from noise, challenge assumptions, and translate complex findings into decisions and actions. This is not a reporting or dashboard-development role. Internal Claims Fraud Analytics is an evolving capability, giving you an exciting opportunity to shape our analytical roadmap, lead-generation approach, data foundation, and future fraud detection capabilities.

Requirements

Experience in fraud, investigative, risk, audit, SIU, or similarly hypothesis-driven analytics.
Experience analyzing claims data: navigate complex relationships across claims, exposures, payments, parties, employees, vendors, and other claims-related data.
Strong stakeholder orientation: actively listen, challenge and reframe requests when needed, establish clear objectives and expectations, facilitate working sessions, influence prioritization toward the highest-value opportunities.
Strong analytical judgment and intellectual curiosity: follow unexpected signals, challenge assumptions, determine whether an apparent anomaly represents meaningful risk.
Proven ability to independently lead complex analyses with limited direction, from initial problem framing through recommendation and implementation.
Ability to thrive in an ambiguous, evolving environment and help create structure, repeatability, and best practices as the capability matures.
Advanced SQL or SAS: complex joins, large datasets, multiple grains of data, query optimization, validation, and development of reusable analytical assets.
Bachelor's Degree plus a minimum 5 years, typically 7 or more years, of related experience required; Mathematics, Economics, Statistics or other quantitative field are preferred fields of study.
Advanced proficiency in Excel (VBA, macros, scripts, formulas, data visualization, etc.), PowerPoint, and statistical software packages (SAS, Emblem).
Must have good planning, analytical, decision-making and communication skills.
Ability to present data, visually and verbally, to guide conversations with business managers.

Nice To Haves

Master's Degree preferred; advanced education may be substituted for years of experience (Ph.D. with no professional experience).
Deep knowledge of data sources, tools and business drivers.
Ability to apply advanced analytical concepts to improve business outcomes.
Ability to build analytic tools that will be used by business teams to analyze results and opportunities.

Responsibilities

Lead complex claims fraud analyses by translating ambiguous investigative questions into clear hypotheses; leverage sound analytical methods to develop recommendations.
Conduct exploratory data analysis of claims, payment, employee, and vendor data to proactively identify suspicious patterns, anomalies, control gaps, and emerging fraud risks.
Improve the fraud lead-generation lifecycle from initial hypothesis development through signal development, validation, investigator handoff, outcome feedback, and iterative refinement.
Develop investigator-ready, comprehensive analyses, not just data pulls; helping stakeholders understand which leads to prioritize and why.
Partner closely with the Claims Fraud Investigation team to validate signals, improve lead efficacy, prioritize opportunities, and measure investigative outcomes.
Partner with Data Science Modeling and tech teams to translate key analytical findings, like fraud indicators, into model-ready inputs.
Independently manage multiple analytics priorities, proactively set expectations, surface tradeoffs, resolve roadblocks, and influence prioritization based on business value.
Synthesize complex analysis into concise, compelling recommendations and clearly communicate findings, implications, and tradeoffs to senior leaders.
Develop reusable datasets, queries, and documentation to strengthen team's data foundation and accelerate future analysis.