Fraud Detection based on Supervised ML data models

Fraudulent claims can be assessed and flagged, prior to reimbursement, using an advanced machine learning component that analyses available structured claim data.

Waste Assessment based on a proprietary data base

Assess the healthcare expenditures invoiced by healthcare providers to insurance companies, in hospitalizations. Evaluates costs of services and frequencies of services invoiced by healthcare providers, compares charges for consumables to market prices, checks actual quantities compared to expected as defined by physicians and healthcare experts. A comparison of the invoiced prices with the market prices is made and an explanatory report is delivered.

Fraud Detection based on network analysis

The network analysis component combines ultra-modern technologies to enhance the insurance claims evaluation process. Using the claim information data, the network analysis component generates a possible fraud network map, including various parties (individuals and service providers) that may be involved in possible fraud or waste.

Fraud Detection based on empirical rules

This component applies standard empirical rules to the data in order to flag possible fraudulent cases.

Fraud Detection based on ML Unsupervised models

Fraudulent claims can be assessed massively and flagged, prior to reimbursement, using an advanced machine learning component that analyses available structured claim data.

Fraud Detection based on financial data analysis

This component applies dynamic comparative analysis in order to identify fraud cases based on the claim size data.