Forecasting automobile insurance paid claim costs using econometric and ARIMA models by J. David Cummins, Gary L. Griepentrog.
Automobile insurance companies in the United States currently utilize simple exponential trend models to forecast paid claim costs, an important variable ratemaking. This paper tests performance of econometric and ARIMA models, as well current industry method, forecasting two cost series. The experiments encompass eight periods ranging from 1974 through early 1983. results indicate that automobile insurers could significantly improve their forecasts property damage liability costs by adopting models. For bodily injury accuracy methods is approximately same, both outperform Overall, a net gain be achieved
Read Forecasting automobile insurance paid claim costs using econometric and ARIMA models on OA.mg