Pondera supports the federal government’s efforts to identify individual cases of fraud or abuse as well as trends, patterns, and clusters that may indicate existing or emerging problems.
Request a DemoPondera is built on a scalable, modular architecture that can rapidly analyze the massive data sets found in many federal government programs. Using a combination of third-party databases, rules-based analysis, prediction algorithms, and machine learning, the system can help federal government agencies validate program beneficiaries, service providers, and discrete transactions. This helps the government identify individual cases of fraud or abuse as well as trends, patterns, and clusters that may indicate existing or emerging problems.
Pondera’s system detects, prevents, and deters fraud, waste, and abuse with enhanced provider screening for new and re-enrolling entities in Medicare and Medicaid programs. Advanced analytics, third party data, and a deep understanding of policy inform our models to prevent ineligible providers and suppliers from entering the program. Integration of third party data into provider enrollment application information generates a 360 degree profile of providers for compliance assessment.
Stakeholders in both public and private healthcare utilize Pondera as a key component in their program integrity efforts. Pondera offers fraud detection in Medicare and Medicaid Fee-For-Service, Medicare Advantage, and Medicaid Managed Care programs. Our specialized detection models include functionality for eligibility validation, provider analysis, and suspicious claims/encounter detection. Transaction data analytics establish strong benchmarks for public and private payors to undertake performance audits to ensure quality and efficient service delivery.
Pondera validates identities with a combination of analytics, third party data, and out-of-wallet questions to ensure that individuals are authentic and eligible for government programs.
Pondera analyzes hundreds of millions of claims annually with a combination of diagnosis code, procedure, and policy rules. Our system also visualizes claims over time which helps agencies to identify patterns, anomalies, and suspicious transactions.
Pondera’s powerful link analysis platform identifies connections between providers, beneficiaries, and facilities. Investigators can visualize complex fraud networks by geography, hierarchy, and time.
Pondera’s system employs alerts, prediction algorithms, and machine learning designed specifically for social services programs to analyze program violations related to retailers. This includes suspicious transactions, collusive networks, card misuse, and stolen identities.
Pondera uses prediction algorithms and machine learning to predict, detect, and investigate fraud, waste, and abuse in healthcare and government programs.
Program data and 3rd party data are ingested and run through procedural and prediction models to detect previously known and unknown bad actors, schemes, and patterns.
Fully-integrated investigative case management imports cases from the fraud detection module or other sources and uses workflow and rules engines to route cases through your resolution process.
Enable your team to protect your public benefits program from the risk associated with potentially fraudulent and improper payments with Thomson Reuters ID Risk Analytics.
Discover how analysts, investigators, and managers leverage Pondera’s system to improve efficiency and deliver results.
Pondera gives analysts the ability to view comprehensive program data, matched against third party data sources, and run through a series of procedural and predictive models.
Pondera helps investigators both in the field and in the office, to streamline workflows and make tracking cases easy through cloud integration.
Pondera’s CaseTracker™ allows managers to easily track and manage cases and case files, get detailed team performance metrics.
Our industry experts are happy to provide an in-person or web conference overview that is customized to your organization and your needs.