Application of GIS in auto insurance risk segmentation and rating: a case for Nairobi county
Abstract
Developments in Geographic Information Systems (GIS) have given rise to sophisticated scientific
techniques for collection, analysis and visualization of location based data. GIS analysis is used to
reveal some critical patterns of occurrences that are not usually obvious. Due to inaccurate analysis
and covering of risks in Kenya, several companies have closed down prompting the Insurance
Regulatory Authority (IRA) and Association of Kenyan Insurers (AKI) set up maximum and
minimum premium rates on insurance risks. The set premiums discounts are given to the insured
based on their annual claims records. The main problem is that the rates cover the entire nation
without considering the distribution of risk in various regions. The main objective of this research
was to show that GIS can be used to analyse and generate auto insurance risk territories for
insurance companies in Nairobi County from which an insurance rating model can be developed.
GIS analysis methods such as Inverse Distance Weighting (IDW) interpolation, data smoothing
and clustering techniques were used. Auto Insurance accidents and crime, geo-coded police
stations, roads, socio-economic, aerial and satellite imagery data for Nairobi County was used. A
risk territory map showing the distribution of Auto insurance risk and other related maps were
generated. A prescriptive insurance rating model auto rating model was developed that uses
generated risk territories limits to calculate varying rates for auto insurance premiums rates for the
respective regions. This research shows that GIS techniques can be used for better visualization of
risk at a given location for accurate risk analysis and uptake. This research can also be applied to
other locations and classes of risks as well as calculating upfront discounts on Auto insurance
premium rates.
Keywords: Auto Insurance Rating Model, Auto Insurance Risk Territory, Auto Insurance
Accidents and Crime, Inverse Distance Weighting (IDW), Prescriptive, Spatial Interpolation
Publisher
University of Nairobi
Description
Masters