From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review
Abstract
Claims data can show that provider behavior changed but cannot by itself explain why. Fraud, waste, and abuse (FWA) review requires identifying material behavior, locating the codes and dollars driving it, and testing plausible explanations. Forecast residuals conflate growth, service-line shifts, code maintenance, and incomplete observation with potentially concerning behavior. We instead formulate provider review as a descriptive representation problem: observed amount yijt=sitpijt, where sit is provider scale and pijt is procedure composition. The profile records scale history, effective-dated code lineage, clinical-family shares, first-use events, billing context, and Medicare-versus-client differences. An optional rank-32 nonnegative factorization of procedure co-occurrence adds a fixed semantic geometry for similarity and retrieval. The profile surfaces evidence for review without inferring intent or adjudicating FWA, and is one engine within Falcon's broader review system. In a ten-quarter proprietary Medicare Carrier and DME build (1.27 million providers; 9.2 million provider-quarter profiles through 2026~Q2), the semantic dictionary covers 3,641 procedures and raises recall at 10 from 36.0\% to 44.4\%; for high-cost rare events, recall at 50 is 56.1\% versus zero for popularity. Under the governed eligibility contract, 414,093 providers enter the national review population, with 81.8\% and 90.8\% remaining eligible across adjacent quarters. Replication across eight client panels preserves 86.9--95.2\% amount-weighted semantic coverage. Transparent descriptions thus form the core, with learned representations adding optional semantic context.
Related
- An explainable machine learning framework for cross-dataset chronic kidney disease risk prediction using hybrid data balancing
- Graph-Enhanced Knowledge Tracing for Explainable Learner Modeling: A Systematic Literature Review
- A hybrid car-following behavior prediction framework for snowy weather based on stacking ensemble learning
- Who pays for urban environment management? The role of the third-party service provider
- Cardiovascular risk prediction models for women: A systematic review protocol
BibTeX
@misc{park2026from,
title = {{From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review}},
author = {Yubin Park and Evan Brociner},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28477},
eprint = {2609.28477},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28477},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review
AU - Yubin Park
AU - Evan Brociner
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.28477
UR - https://arxiv.org/abs/2609.28477
AB - Claims data can show that provider behavior changed but cannot by itself explain why. Fraud, waste, and abuse (FWA) review requires identifying material behavior, locating the codes and dollars driving it, and testing plausible explanations. Forecast residuals conflate growth, service-line shifts, code maintenance, and incomplete observation with potentially concerning behavior. We instead formulate provider review as a descriptive representation problem: observed amount y_ijt=s_itp_ijt, where s_it is provider scale and p_ijt is procedure composition. The profile records scale history, effective-dated code lineage, clinical-family shares, first-use events, billing context, and Medicare-versus-client differences. An optional rank-32 nonnegative factorization of procedure co-occurrence adds a fixed semantic geometry for similarity and retrieval. The profile surfaces evidence for review without inferring intent or adjudicating FWA, and is one engine within Falcon's broader review system. In a ten-quarter proprietary Medicare Carrier and DME build (1.27 million providers; 9.2 million provider-quarter profiles through 2026~Q2), the semantic dictionary covers 3,641 procedures and raises recall at 10 from 36.0\% to 44.4\%; for high-cost rare events, recall at 50 is 56.1\% versus zero for popularity. Under the governed eligibility contract, 414,093 providers enter the national review population, with 81.8\% and 90.8\% remaining eligible across adjacent quarters. Replication across eight client panels preserves 86.9--95.2\% amount-weighted semantic coverage. Transparent descriptions thus form the core, with learned representations adding optional semantic context.
ER -