Download PDF
IBM > Case Studies > A major US insurance company improves online insurance fraud detection
IBM Logo

A major US insurance company improves online insurance fraud detection

Technology Category
  • Analytics & Modeling - Real Time Analytics
  • Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries
  • Finance & Insurance
Applicable Functions
  • Procurement
Use Cases
  • Fraud Detection
Services
  • Data Science Services
The Challenge
The major US insurance company was facing challenges in pinpointing fraud quickly on submitted claims and strengthening prevention methods. With each investigator handling 35 investigations, the business needed to accurately and quickly ingest data from multiple sources, including policy, claims and medical billing data; Insurance Services Office (ISO) data; and public records data from the Thomas Reuters CLEAR database to build links and find relationships among fraudsters and the people and businesses they are related to. In addition to determining whether a claim was legitimate, the company believed that gaining insight into customers before granting them insurance would help prevent fraud. It sought a system to help bolster fraud prevention and detection capabilities.
About The Customer
The customer is a major US insurance company headquartered in Chevy Chase, Maryland. The company provides online auto and medical coverage to more than 15 million customers in all 50 states and Puerto Rico. Using a direct-to-market sales model, the organization employs 24,000 people and relies on multiple TV advertising campaigns rather than agent-based sales to generate revenue. The company works hard to prevent and detect auto and medical insurance fraud and prosecute perpetrators. It strives to pay, deny or hold any claim for further investigation in 20 days, as opposed to the industry standard of 30 days.
The Solution
The company implemented IBM i2 software in its continued fight to prevent and detect auto and medical insurance fraud. The business purchased multiple licenses for IBM i2 Analyst’s Notebook®, IBM i2 iBridge and IBM i2 Text Chart software, which it uses to ingest reports and data from all sources and quickly transform unstructured data into a clear format. The solution helps the company ingest IP addresses, scanned document references, email addresses, driver’s license information, criminal records, judgments or known fraudulent connection data to link multiple sources and identify relationships that may otherwise remain anonymous. The world-class visualization capabilities of i2 software help the company take hundreds of thousands of data points and highlight repeatable patterns, pinpointing entities involved and associated connections and identifying commonalities that may lead to claim denial.
Operational Impact
  • The company now quickly discovers repeatable patterns to identify fraudulent claims and save the company and its customers money.
  • The solution provides stronger fraud protection by assimilating multiple data types.
  • The solution helps identify hidden or anonymous relationships.

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.