6 résultats pour « neuralnetworks »

Learning Inter‑Annual Flood Loss Risk Models from Historical Flood Insurance Claims

This research evaluates different regression models to predict #flood-induced #insuranceclaims, using the #us #national #floodinsurance Program (#nfip) dataset from 2000 to 2020. The models studied include #neuralnetworks (Conditional Generative Adversarial Networks), #decisiontrees (Extreme Gradient Boosting), and #kernel-based regressors (#gaussian Process). The study identifies key predictors for regression, highlighting factors that influence flood-related financial damages.

Prediction of Auto Insurance Risk Based on t‑SNE Dimensionality Reduction

"... we develop a framework based on a combination of a neural network together with a dimensionality reduction technique t-SNE (t-distributed stochastic neighbour embedding)... The obtained results, which are based on real insurance data, reveal a clear contrast between the high and low risk policy holders, and indeed improve upon the actual risk estimation performed by the insurer."

A parametric approach to the estimation of convex risk functionals based on Wasserstein distance

" 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."