A representation-learning approach for insurance pricing with images

TL;DR

This paper introduces a novel framework that leverages representation learning to incorporate street view images into insurance pricing models, enhancing risk prediction accuracy.

Contribution

It presents a new method to extract meaningful features from unstructured image data for use in existing insurance ratemaking models.

Findings

Street view imagery contains useful information for predicting claim frequency.

The embedding vectors are dense and low-dimensional, suitable for model integration.

The approach opens avenues for future causal analysis of image data in insurance risk assessment.

Abstract

Unstructured data are a promising new source of information that insurance companies may use to understand their risk portfolio better and improve the customer experience. However, these novel data sources are difficult to incorporate into existing ratemaking frameworks due to the size and format of the unstructured data. In this paper, we propose a framework to use street view imagery within a generalized linear model. To do so, we use representation learning to extract an embedding vector containing useful information from the image. This embedding is dense and low-dimensional, making it appropriate to use within existing ratemaking models. We find that there is useful information included in street view imagery to predict the frequency of claims for certain types of perils. This model can be used as-is in a ratemaking framework but also opens the door to future empirical research on attempting to extract the causal effect from images that lead to increased or decreased predicted claim frequencies. Throughout, we discuss the practical difficulties (technical and social) of using this type of data for insurance pricing.