Please Note: This seminar will be given online.
University of Wisconsin-Madison
Link to join seminar: Hosted on Zoom
A Marked Spatial Point Process for Insurance Claims Management
Technological advances in data collection indicate growing potential for analytics to support efficient claims management. We demonstrate how insurers can incorporate high-resolution weather data to assess hail property damage immediately following a hailstorm. In particular, we propose a marked spatial point process for replicated point patterns to model the frequency and severity of hail damage insurance claims. The point process focuses on the geographical distribution of claims and allows insurers to simultaneously incorporate densely collected weather features and traditional policyholder-level rating characteristics, despite being observed from different locations. The marks concern the financial impact of a hailstorm, particularly the effects of dependence among claims. We employ a spatial factor copula to capture spatial dependence, allowing insurers to decompose sources of dependence when jointly characterizing claim severity. Using hail damage insurance claims data from a U.S. insurer, supplemented with hail radar maps and other spatially varying weather features, we show that incorporating granular data to model the development of claim reporting patterns helps insurers anticipate and manage claims more efficiently.