Performance evaluation of the Bühlmann credibility approach in predicting mortality rates

Modeling mortality is an important thing for insurance company in determining the appropriate premium for a policy holder. This paper explains the Bühlmann credibility approach for modeling mortality. Bühlmann's credibility model is generally used to predict the value of a random variable in the next future period. In predicting the value of a random variable in the next two or more future periods, an approach is needed. In this paper, the Bühlmann credibility approach is done through 2 strategies: the expanding window strategy and the moving window strategy. The expanding window strategy is done by adding the predicted value to the data to produce a predicted value in the following year while the moving window strategy is done by adding the predicted value to the data and discarding the oldest data to produce a predicted value in the following year. Mortality prediction performances from the Bühlmann credibility approach are being analysed by comparing the values of AAMAPE and the reduction ratio of the Bühlmann credibility approach to the Lee-Carter model. From this paper, it was found that the Bühlmann credibility approach produced better mortality predictions compared to the Lee-Carter model in case of Australian mortality data.