Data organization analysis in mortgage insurance: The implications of dynamic risk characteristics

  • Print
  • Connect
  • Email
  • Facebook
  • Twitter
  • LinkedIn
  • Google+
By Kyle Mrotek , Tanya Havlicek | 01 January 2008

The ability to establish loss reserves conditioned on delinquency status, a dynamic risk characteristic, presents particular data issues for mortgage guaranty insurance companies. There is a need to collect, organize, warehouse, and analyze large data sets that contain loan-level detail over consecutive evaluation dates in order to measure the probability of claim, conditioned on delinquency status. The generally accepted methodology of reserving for mortgage guaranty insurance claim liabilities requires evaluation of dynamic risk characteristics because mortgage guaranty insurance companies need only reserve for loans currently delinquent, both known and IBNR. Because each loan’s delinquency status is usually revised monthly by the mortgage servicing company, the cohort of insured loans currently delinquent changes each month and therefore is dynamic with respect to time. Coincidentally, delinquency status has been found to be a strong predictor of future losses, so it is imperative for mortgage guaranty insurance companies to estimate reserves as a function of delinquency status, a dynamic risk characteristic. Maintaining historical economic factors in step with the historical delinquency and claim data can also enhance the reserving approach.

First appeared in the Casualty Actuarial Society E-Forum, Winter 2008.