INSURANCE CLAIMS PROCESSING

OVERVIEW

This case study is based on data from a large global insurance company which is engaged in providing Auto 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 repetitive and time consuming but critical for employee satisfaction. To overcome this, we developed and implemented RPA (Robotic Process Automation) for monitoring the incoming customer claims received via emails in the form of PDF. Our solution captures the required data from each claim which is then populated in the Master excel sheet and emailed to the company’s head of claims. In addition, the 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 a high risk/low risk prediction for each claim that are emailed out to 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

RESULTS & BENEFITS

• Reduced Costs and Operational Risks.
• Better employee utilization
• Agent and client satisfaction both improved
• Able to develop and deploy solution with existing IT Infrastructure
• Improved process efficiency.
• Faster and reliable Service.

Typical Challenges for Claims Processing:

• Possibility of Human errors
• Additional number of dedicated employees in claims department.
• Inaccuracy in data validation.
• Difficulty in identifying fraudulent Vs. Genuine claims
• Overall decrease in employee productivity performing manual/routine tasks.
• Excessive resource time wasted to check fraudulent claims

SOLUTION

Our goal was to explore how RPA and AI can lead to automate Claims processing and reduce fraud. After thoroughly evaluating the client’s challenges, we used UI Path to automate the various steps in claims processing. Our AI Engine then processes the claims and rates them as High Fraud Risk or Low Fraud Risk for appropriate processing.
The typical RPA and AI process for this project involves:

• The bot monitors the incoming email claims from the customers (PDF format) and processes each of these forms.
• The bot captures the required data from each form with the help of OCR and populates all the claims in to a Master Excel sheet
• The daily Master excel sheet is sent via email to the Company’s Head of Claims with the Original Claims form from the customer embedded in the row. This is also used for potential fraud Predictions against trained AI Models and assigned to the appropriate Claims adjusters accordingly
• After processing all claims and creation of Excel sheet, the bot also uploads the daily data to the company’s claim system (Optional)