This case study is based on data from a large global insurance company which is engaged in providing health insurance. With offices in multiple countries, the claims department handles various activities such as processing and approving claims etc. Each of these processes comprise of several activities that are time consuming but critical for employee satisfaction. This solution leverages our Minsky™ AI engine to categorize each claim as High Risk or Low Risk based on the customers historical data. Minsky™ then creates accurate Modes that can be used to process live data for high risk/low risk to be handled by the appropriate claims adjuster based on the rating for further processing. This real time monitoring/actions helped us automate the claims processing across various geo locations offices while also reducing fraudulent claims. Solution was integrated with an existing system.
KEY BENEFITS (MINSKY™)
- User-Friendly, cloud based AI platform
- No coding skills are required for results or predictions.
- Provides you a list of % dependency features that can be used to optimize your business
- Ability to fine tune or optimize the models by trying different algorithms / prediction attributes
- Easy integration with other third party solutions such as TABLEAU for data visualization
RESULTS & BENEFITS:
- Optimized Claims Management for Reduced Costs and Operational Risks.
- Better employee utilization.
- Able to develop and deploy solution with existing IT Infrastructure.
- Improved process efficiency.
- Faster and reliable Service.
Typical Challenges for Claims Processing:
- Almost one in ten claims is incorrect and the claim’s amount can be challenged by the health insurer
- As a rule, as many as 70 percent of claims are flagged as unusual – i.e., as potentially incorrect – based on the health insurer’s specific rule book.
- Claims audits absorb valuable manpower, time, and resources that could be put to better use elsewhere – not just at health insurers, but also at providers to check fraudulent claims.
- Difficulty in identifying fraudulent Vs. Genuine claims
- Excessive resource time wasted to check fraudulent claims.
Our goal was to explore how AI can lead to automate Claims processing and reduce fraud. After thoroughly evaluating the client’s challenges, we used our AI Engine to process the claims and rate them as High Fraud Risk or Low Fraud Risk for appropriate processing. The typical AI process for this project involves:
- Compile and preprocess data
- Analyze data
- Develop and train the Ai models
- Evaluate the results that will ultimately be used, several cognitive systems are programmed and then benchmarked in terms of specific metrics.
- Finally, the system is optimized to most reliably predict the likelihood that a claim can be reduced successfully
- Pilot the approach: The final piloting phase serves to audit new claims received in real-world conditions and optimize the algorithms continuously.