Increase in fraud was a serious threat to one of the leading insurance companies in the U.S. Nuvento implemented an automated reporting mechanism that detects possible frauds, made by claims representatives during the settlement of an auto liability or casualty claim.

Fraud is one of the biggest challenges for an insurance company. The high increase in deception is costing the industry billions of dollars every year. Payments of false claims weakens the financial position of the organization and also undermines its ability to underwrite potentially profitable business. Fraud management is one of the top priorities for insurance companies worldwide.

Managing fraud is a difficult and complicated task since it is diverse in nature and across every kind of insurance. The large customer base and volumes of data across multiple sources increase the complexity.

Nuvento’s client, one of the largest insurance companies in the U.S. was encountering a similar situation. The organization had to prevent fraudulent activities across 8 million payments made over 3.5 million claims covering the auto liability and casualty lines of business.

  • It is difficult to get a comprehensive view of a customer, account history and transaction path as the data is available in silos.
  • With increased focus on customer satisfaction, insurers are reluctant to delay the processing of a claim based on a hunch or worse wrongly target a legitimate claim.
  • Manual analysis of large volumes of claims is tedious and in most cases inaccurate.
  • A significant part of the data around claims is available in free text. It is difficult to analyze this unstructured data

 Based on its strong experience and deep domain knowledge, the insurance company selected Nuvento’s Business Intelligence (BI) solutions to build a fraud management system. We focused on providing solutions that could mitigate diverse risks, had strong thresholds and would ultimately contribute to cost savings for the client.

  • All the historical fraud and transactional data was analyzed to identify risks and fraud patterns.
  • Nuvento used a predictive model to determine the fraud potential, employing a statistical algorithm. Data mining tools and programs were built to produce fraud propensity scores. Claims are automatically scored on their likelihood to be fraudulent.
  • Sentiment analysis on free form text helped to determine the gaps in the claim lifecycle. This method of analysis assists in discovering the attitudes and behavior across the data being analyzed.
  • Nuvento used its proprietary product BI Report Center which provided web-based reporting, organized data in OLAP models and provided an analytics solution. Additional features include data pivots and 3D graphs.
  • Siebel’s claims system was used to get a detailed drill down of customer information thus extracting data from claims, reserves and payments.
  • The intelligent information used to detect fraud, was also aggregated from employee based data using Oracle Employee Management System.
  • The Nuvento solution included other features of BI such as advanced data visualizations, data mining, accelerators, query optimization, third-party integration, operational data store, data warehouse and data marts.
  • Nuvento Implemented a customer specific fraud scoring mechanism based on 20 distinct parameters.
  • The fraud management system was supported with the best-in-class database management systems:
    • SQL Server Analysis Services (SSAS)
    • SQL Server Reporting Services (SSRS)
    • SQL Server Integration Services (SSIS)
    • .NET Framework 3.5
  • The insurance company now had a comprehensive system to mitigate risks across the auto liability and casualty lines of business.
  • The client also saw improved profitability with reduced payments for fraudulent claims.
  • Nuvento was able to organize data to view reports within 5 seconds.
  • Predictive modelling is more accurate than any other fraud detection method. Information could now be collected and cross referenced across a variety of sources.
  • The insurance company was able to detect more than 20,000 possible chances of frauds.
  • With the Nuvento solution, the insurance company was able to capture all fraud outcomes, referrals and suspects within the system. This helped in the detection of repeat offenders and more accurate validation of incoming claims.
  • The client is now able to view all claims from a customer across all lines of business.
Insurance-BI