Nos derniers articles

This paper focuses on the development of #bayesian classification and regression tree (#cart) models for claims frequency modeling in non-life #insurance pricing. The authors propose the use of the zero-inflated #poisson distribution to address the issue of imbalanced claims data and introduce a general MCMC algorithm for posterior tree exploration. Additionally, the deviance information criterion (DIC) is used for model selection. The paper discusses the applicability of these models through simulations and real insurance data.

"We present a novel approach to quantify the uncertainty and sensitivity of risk estimates, using the CLIMADA open-source climate risk assessment platform. This work builds upon a recently developed extension of CLIMADA, which uses statistical modelling techniques to better quantify climate model ensemble uncertainty. Here, we further analyse the propagation of hazard, exposure and vulnerability uncertainties by varying a number of input factors based on a discrete, scientifically justified set of options."

"We respond to Tetlock et al. (2022) showing 1) how expert judgment fails to reflect tail risk, 2) the lack of compatibility between forecasting tournaments and tail risk assessment methods (such as extreme value theory). More importantly, we communicate a new result showing a greater gap between the properties of tail expectation and those of the corresponding probability."

"Bayesian estimates from experimental data can be influenced by highly diffuse or "uninformative" priors. This paper discusses how practitioners can use their own expertise to critique and select a prior that (i) incorporates our knowledge as experts in the field, and (ii) achieves favorable sampling properties. I demonstrate these techniques using data from eleven experiments of decision-making under risk, and discuss some implications of the findings."

" In this paper, we use stochastic algorithms schemes in estimating MSRM [market data based systemic risk measure] and prove that the resulting estimators are consistent and asymptotically normal. We also test numerically the performance of these algorithms on several examples."

"Our paper contributes to the theory of conditional risk measures and conditional certainty equivalents. We adopt a random modular approach which proved to be effective in the study of modular convex analysis and conditional risk measures."

"This paper extends the traditional multi-state models to include epidemic effects."

"... we propose a reverse stress testing framework for dynamic models. Specifically, we consider a compound Poisson process over a finite time horizon and stresses composed of expected values of functions applied to the process at the terminal time. We then define the stressed model as the probability measure under which the process satisfies the constraints and which minimizes the KullbackLeibler divergence to the reference compound Poisson model."

"When developing large-sample statistical inference for quantiles, also known as Values-at-Risk in finance and insurance, the usual approach is to convert the task into sums of random variables. The conversion procedure requires that the underlying cumulative distribution function (cdf) would have a probability density function (pdf), plus some minor additional assumptions on the pdf. In view of this, and in conjunction with the classical continuous-mapping theorem, researchers also tend to impose the same pdf-based assumptions when investigating (functionals of) integrals of the quantiles, which are natural ingredients of many risk measures in finance and insurance. Interestingly, the pdf-based assumptions are not needed when working with integrals of quantiles, and in this paper we explain and illustrate this remarkable phenomenon."

" The aim is to come up with a convex risk functional that incorporates a sefety margin with respect to nonparametric uncertainty and still can be approximated through parametrized models. The particular form of the parametrization allows us to develop a numerical method, based on neural networks, which gives both the value of the risk functional and the optimal perturbation of the reference measure."