Mack-Net model: Blending Mack's model with Recurrent Neural Networks

TL;DR

This paper introduces a novel stochastic reserving model that combines Mack's traditional model with Recurrent Neural Networks, enhancing the accuracy of liability estimation in insurance by leveraging deep learning techniques.

Contribution

It presents a new ensemble approach that integrates Mack's model with RNNs, improving liability prediction accuracy in insurance reserving.

Findings

Enhanced liability estimation accuracy.

Better risk assessment through deep learning integration.

Outperforms traditional Mack's model in experiments.

Abstract

In general insurance companies, a correct estimation of liabilities plays a key role due to its impact on management and investing decisions. Since the Financial Crisis of 2007-2008 and the strengthening of regulation, the focus is not only on the total reserve but also on its variability, which is an indicator of the risk assumed by the company. Thus, measures that relate profitability with risk are crucial in order to understand the financial position of insurance firms. Taking advantage of the increasing computational power, this paper introduces a stochastic reserving model whose aim is to improve the performance of the traditional Mack's reserving model by applying an ensemble of Recurrent Neural Networks. The results demonstrate that blending traditional reserving models with deep and machine learning techniques leads to a more accurate assessment of general insurance liabilities.