Invert-Logo
Advanced Analytics Helps in Fraud Detection - Case Study
Case Study

Advanced Analytics Helps in Fraud Detection for a Leading Healthcare Giant

Client

The client is a prominent healthcare and insurance provider group serving over 30 million customers across healthcare products and services, health insurance, health centers, care homes, travel insurance and dental care.


Industry

Healthcare

Challenges

The client received huge volumes of claims which consumed time for processing. Data attributes in the claims was measured on numerous scales which made data processing, preparation, transformation and consumption extremely difficult.

The client wanted to develop a sophisticated rules engine that would not just be capable of detecting fraudulent claims in real time, but also would get better with time as it is exposed to more data by leveraging Artificial Intelligence in order to curb the financial losses due to fraudulent claims.

Solution

Datamatics aimed at developing a sophisticated rules engine that would not just be capable of detecting fraudulent claims in real time through algorithmic interventions, but also capable of improving itself leveraging machine learning with increased exposure to data.

Datamatics studied the raw data set vis-à-vis both the claim values as well as the invoice lines. The team segregated the attributes in terms of Age, Claim Invoice Gross GBP, and Claim Invoice Net GBP. They also divided the attributes as Gender, Country Code, Diagnostic Code, Claim Status, Policy Type, etc., for the actual values.

Datamatics implemented an ensemble of machine learning techniques coupled with anomaly detection to analyse 3.3 million claims to identify potentially fraudulent claims within the formed clusters. Complex technological interventions utilized to devise a user-friendly interface capable of detecting fraudulent behavior in real time.

Granular line item level data comprising of several attributes in all possible scales (nominal, ordinal, interval and ratio) was utilized and challenges related to non-availability of markers were addressed with ingenuity.

Impacts

3.3 million Number of claims analysed and 65k outliers identified

3.3 million

Number of claims analysed and 65k outliers identified

80% Efficiency rate of the solution

80%

Efficiency rate of the solution

Unearthed higher fraud propensity Claimant age is 31-40 years

Unearthed Higher Fraud Propensity

Claimant age is 31-40 years

Country Index Score Derived from fraud propensity

Country Index Score

Derived from fraud propensity