Conformal prediction for frequency-severity modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Graziadei, Helton, F., Paulo C. Marques, de Melo, Eduardo F. L., Targino, Rodrigo S.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915580148187136
author Graziadei, Helton
F., Paulo C. Marques
de Melo, Eduardo F. L.
Targino, Rodrigo S.
author_facet Graziadei, Helton
F., Paulo C. Marques
de Melo, Eduardo F. L.
Targino, Rodrigo S.
contents We present a model-agnostic framework for the construction of prediction intervals of insurance claims, with finite sample statistical guarantees, extending the technique of split conformal prediction to the domain of two-stage frequency-severity modeling. The framework effectiveness is showcased with simulated and real datasets using classical parametric models and contemporary machine learning methods. When the underlying severity model is a random forest, we extend the two-stage split conformal prediction algorithm, showing how the out-of-bag mechanism can be leveraged to eliminate the need for a calibration set in the conformal procedure.
format Preprint
id arxiv_https___arxiv_org_abs_2307_13124
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Conformal prediction for frequency-severity modeling
Graziadei, Helton
F., Paulo C. Marques
de Melo, Eduardo F. L.
Targino, Rodrigo S.
Methodology
Machine Learning
We present a model-agnostic framework for the construction of prediction intervals of insurance claims, with finite sample statistical guarantees, extending the technique of split conformal prediction to the domain of two-stage frequency-severity modeling. The framework effectiveness is showcased with simulated and real datasets using classical parametric models and contemporary machine learning methods. When the underlying severity model is a random forest, we extend the two-stage split conformal prediction algorithm, showing how the out-of-bag mechanism can be leveraged to eliminate the need for a calibration set in the conformal procedure.
title Conformal prediction for frequency-severity modeling
topic Methodology
Machine Learning
url https://arxiv.org/abs/2307.13124