Agricultural Insurance Portfolio Risk Assessment Model
Assoc. Prof. Kasırga Yıldırak, Department of Actuarial Sciences, Hacettepe University
April 6, Friday 13:30
EA-409
Abstract
8 years of claims data collected by Turkish Agricultural Insurance Pool (TARSIM) is analyzed to build a portfolio risk management model for internal reporting, reinsurance pricing and actuarial pricing.
In order to reduce the dimension of data (15000000 X 10), product specific clusters so called hazard regions for hail, frost, flood, fire and storm are formed. Layer based spherical clustering methods where the layers are composed of location, damage ratio and damage probability are used employing distance based spherical k-means, density based finite mixture von-Mises Fisher (and some other clustering techniques embedded in SatScan software).
Information obtained from clusters is used to build the loss distribution associated with entire portfolio. Loss distribution is estimated by Poisson-Gamma actuarial portfolio risk model to compute the economic capital, risk contributions, expected maximum loss and probable maximum loss.
Short Bio of the speaker
Kasirga Yildirak is an Associate Professor in the department of Actuarial sciences at Hacettepe University where he has been a faculty member since 2013. He completed his Ph.D. at Middle East Technical University, Master’s degree in NC State and his undergraduate studies at Ankara University. Previously, He was a faculty member in Institute of Applied Math of METU, and Department of Economics at Trakya University.
His research interests are mostly focused on risk modeling and risk assessment on various areas such as finance, ecology, health and agriculture. He worked on numbers of industrial projects for developing market and credit risk monitoring and measurement systems with several commercial banks and Central Bank of Turkey. He has also supervised FAO of UN on drought risk associated with climate change and its impact on food security, Turkish Agricultural Insurance Pool on actuarial pricing of insurance policies.
