Optimal Selection of Loss Severity Distribution Based on LDA

This paper compares the sensitivity of aggregate operational Value-at-Risk in the Pareto distribution with that in the Weibull distribution to select an optimal model from the loss severity distributions of approximate goodness-of-fit. After the aggregate operational Value-at-Risk is obtained, the sensitivities of aggregate operational Value-at-Risk are compared when the loss severity distribution are respectively the Pareto and Weibull. The sensitivity of aggregate operational Value-at-Risk with the Pareto distribution is far better than that with the Weibull distribution. Accordingly, the sensitivity of supervised system of operational risk with the Pareto distribution is far better than that with the Weibull distribution. And the Pareto distribution is the optimal model of loss severity distributions. This paper not only finds a new approach to select an optimal model from the distributions of approximate goodness-of-fit, but also connects the selection of distributions with the management of operational risk. This research improves the application of loss distribution approach to the measurement of operational risk.