Prediction of Auto Insurance Risk Based on t-SNE Dimensionality Reduction

TL;DR

This paper introduces a neural network combined with t-SNE for visualizing and improving auto insurance risk estimation, providing clearer risk differentiation and potential for enhanced decision-making.

Contribution

It presents a novel framework integrating neural networks with t-SNE for risk visualization and improved estimation in auto insurance.

Findings

Clear risk contrast between high and low policyholders

Improved risk estimation accuracy over existing methods

Visual representation aids in risk assessment validation

Abstract

Correct risk estimation of policyholders is of great significance to auto insurance companies. While the current tools used in this field have been proven in practice to be quite efficient and beneficial, we argue that there is still a lot of room for development and improvement in the auto insurance risk estimation process. To this end, we develop a framework based on a combination of a neural network together with a dimensionality reduction technique t-SNE (t-distributed stochastic neighbour embedding). This enables us to visually represent the complex structure of the risk as a two-dimensional surface, while still preserving the properties of the local region in the features space. The obtained results, which are based on real insurance data, reveal a clear contrast between the high and the low risk policy holders, and indeed improve upon the actual risk estimation performed by the insurer. Due to the visual accessibility of the portfolio in this approach, we argue that this framework could be advantageous to the auto insurer, both as a main risk prediction tool and as an additional validation stage in other approaches.