Situation

Our client develops software for the Property & Casualty industry and processes millions of insurance claims per year.

insurance

Each month, this client enables hundreds of insurance companies to process millions of claims transactions

During the estimate process, the insurance adjusters review damaged vehicles and manually enter information, a cumbersome task with a high risk of human error.

Action

Infogain developed an intelligent recommendation engine to automate claims estimating, one of the largest and most important steps of the claims process. The solution makes intuitive vehicle part recommendations based on the vehicle’s make and model, year, operation code, and part codes. It also estimates labor hours and other costs. This AI-driven recommendation engine solution includes:

  • Integration with three existing client products
  • Machine learning (ML)-based application programming interfaces (APIs) that recognize objects in uploaded images
  • ML-based APIs to identify and categorize a selected product
  • ML-based recommendation engine that suggests automotive parts
  • Rich Angular-based user interface (UI) for an efficient user experience

  • Integration points to fetch data from client’s automotive parts database that includes part profiles, images repository, products database, and more

Results

  • Our client has a competitive advantage over most insurance companies that still rely on the error prone manual approach
  • Cost and time savings with an intuitive, ML-based recommendation engine that saves time in manually creating the estimate
  • Lower risk and reduction in human error with more than 92% accuracy in the estimation process
insurance-results-1
1/3

Our machine learning-based recommendation engine eliminates manual entries, lowering the risk of human error and giving our client a competitive advantage

insurance-results-2
2/3

Infogain automated solution enabled the client to achieve 92% accuracy in claims estimation process

insurance-results-3
3/3

More accurate estimates drive efficiency and cost savings

  • 90%

    recommendation-based coverage

  • 92%

    accuracy in estimation