Powered by AWS Cloud Computing

DataRobot awarded prestigious status

"AWS Machine Learning Competency"

Claim Development Modeling

Use DataRobot to predict the ultimate claim amount based on claim characteristics at the time the claim is filed.

Industry

P&C Insurance

Why DataRobot

Click a button and build the most accurate model to predict, at the time of filing, what the final claim amount will be. DataRobot uses not only numbers and characters, but also text features. With the addition of text, you get true insights from variables such as claim adjuster notes, leading to extremely accurate predictive models.

Highlights
  • Predict how much a claim will ultimately cost, allowing you to post accurate reserves
  • Determine a loss variable for use in loss cost models (Ultimate Incurred Losses)

Challenge

In the time between an insurance claim's initial filing and full payment, the amount of the claim can change drastically. The ability to predict the final claim amount has significant impact on financial statements, specifically the reserves and Incurred But Not Reported (IBNR) amounts reported in Quarterly Earning statements. Additionally, loss cost modeling relies on Incurred Loss Amounts, which are undeveloped compared to fully developed loss amounts.

Solution

With DataRobot, you automatically build extremely accurate predictive models that lead to a better understanding of how much a claim will ultimately cost. As a result, you can have confidence in how much to reserve for Incurred But Not Reported Loss Amounts. Using the predicted developed loss for each claim as the dependent variable, you will build more robust, accurate pricing models.

Results:

  • More accurate IBNR estimates
  • Less volatility in reserve changes, quarter by quarter, in financial statements

Do you have a similar case?

Want to see this specific use case in action? Contact us to find out how we can solve your problems.

Contact us