Rethinking Representations in P&C Actuarial Science with Deep Neural Networks

TL;DR

This paper explores how deep neural networks can be used to incorporate emerging data sources like text and images into actuarial models, improving loss prediction in insurance.

Contribution

It introduces a unified framework for transforming diverse data types into dense vector representations for enhanced actuarial modeling.

Findings

Methods for converting non-vector data into vector representations

Examples demonstrating improved loss prediction models

A comprehensive framework for integrating new data sources

Abstract

Insurance companies gather a growing variety of data for use in the insurance process, but most traditional ratemaking models are not designed to support them. In particular, many emerging data sources (text, images, sensors) may complement traditional data to provide better insights to predict the future losses in an insurance contract. This paper presents some of these emerging data sources and presents a unified framework for actuaries to incorporate these in existing ratemaking models. Our approach stems from representation learning, whose goal is to create representations of raw data. A useful representation will transform the original data into a dense vector space where the ultimate predictive task is simpler to model. Our paper presents methods to transform non-vectorial data into vectorial representations and provides examples for actuarial science.