Phillips C.

Key Skills

Software

No software listed

Top Subject Matter

Insurance claims text

fraud indicators

and subrogation scenario labeling

Top Data Types

Text

Document

Top Task Types

Classification

Freelancer Overview

Auto Claims Adjuster (Progressive Insurance) — data labeling for claims automation and test case scenario construction. Brings 5+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, University of Utah (2022). AI-training focus includes data types such as Text and Document and labeling workflows including Classification and Entity (NER).

Labeling Experience

Auto Claims Adjuster (Progressive Insurance) — data labeling for claims automation and test case scenario construction

TextClassification

Served as an Auto Claims Adjuster where you led data labeling initiatives to categorize and annotate historical auto-claim text for internal claims automation. You created structured fraud-flagging scenarios with reason codes and verified correct answers with precise policy citations and payout calculations. You evaluated labeled outputs for absolute accuracy and state-level regulatory compliance to improve downstream automated decisioning. • Labeled and categorized claim text for training internal claims automation software. • Authored fraud-flagging scenarios using structured reason codes for SIU referrals. • Verified labeling correctness via policy citations and payout calculations within authority limits. • Applied state-specific negligence rule logic to build robust subrogation test cases.

2024 - Present

Claims Representative (Bear River Mutual Insurance Company) — semantic annotation and scenario design for ML-ready claims data

Document

Worked as a Claims Representative focusing on FNOL and auto claims adjustment while performing high-quality data labeling and semantic annotation for localized property damage reports. You supported machine learning model training by annotating large volumes of structured damage documentation and maintaining rigorous cross-references to policy exclusions. You also designed complex FNOL scenarios (including contradictions, decoy files, and outdated documents) to stress-test automated agent robustness. • Provided semantic annotation for thousands of localized property damage reports. • Labeled and supported ML training data for auto claims decision workflows. • Designed FNOL scenarios to test automated agent robustness under adversarial/edge conditions. • Maintained documentation standards by cross-referencing policy exclusions with labeled evidence.

2022 - 2023

Education

Work History