Stochastic reserving with a stacked model based on a hybridized Artificial Neural Network

TL;DR

This paper presents a hybrid machine learning approach, stacking neural networks and ensemble methods, to improve insurance reserving accuracy over traditional Bayesian and Chain Ladder models.

Contribution

It introduces a novel stacked model combining neural networks and ensemble techniques for stochastic reserving, enhancing prediction accuracy and risk assessment.

Findings

Improved reserving accuracy compared to traditional models

Effective combination of neural networks and ensemble methods

Enhanced risk assessment for insurance reserves

Abstract

Currently, legal requirements demand that insurance companies increase their emphasis on monitoring the risks linked to the underwriting and asset management activities. Regarding underwriting risks, the main uncertainties that insurers must manage are related to the premium sufficiency to cover future claims and the adequacy of the current reserves to pay outstanding claims. Both risks are calibrated using stochastic models due to their nature. This paper introduces a reserving model based on a set of machine learning techniques such as Gradient Boosting, Random Forest and Artificial Neural Networks. These algorithms and other widely used reserving models are stacked to predict the shape of the runoff. To compute the deviation around a former prediction, a log-normal approach is combined with the suggested model. The empirical results demonstrate that the proposed methodology can be used to improve the performance of the traditional reserving techniques based on Bayesian statistics and a Chain Ladder, leading to a more accurate assessment of the reserving risk.