Modeling Mortgage Insurance as a Multistate Process

Abstract

This paper covers experiences in modeling mortgage insurance claims. In Section 2, mortgage insurance claims are considered an absorbing state in a Markov chain that involves transitions between the states of healthy, in arrears, property in possession, property sold, loan discharged, and claim. Section 3 considers the representation of this process by a cascade of five frequency generalized linear models (GLMs) and a further GLM for claim size. These models are applied to the forecast of technical liabilities in Section 4 and the estimation of the associated forecast error in Section 5.

 

Volume
0001,0001,Spring
Page
0081-0102
Year
2007
Keywords
Earned premium, forecast, forecast error, generalized linear model, loss reserve, Markovian, mortgage insurance, technical liabilities, predictive analytics
Categories
Actuarial Applications and Methodologies
Ratemaking
Credit Scoring
Actuarial Applications and Methodologies
Reserving
Reserve Variability
Actuarial Applications and Methodologies
Reserving
Reserving Methods
Actuarial Applications and Methodologies
Reserving
Unearned Premium Reserves
Business Areas
Other Lines of Business
Publications
Variance
Authors
Peter Mulquiney
Greg C Taylor
Audio