Quantum support vector regression for disability insurance

TL;DR

This paper introduces a hybrid classical-quantum method for modeling disability insurance probabilities using quantum support vector regression, leveraging quantum kernels estimated on a quantum computer to improve predictive modeling.

Contribution

It presents a novel quantum support vector regression approach for insurance modeling, integrating quantum kernels with classical data to enhance predictive capabilities.

Findings

Quantum kernel estimation is feasible on current quantum hardware.

The model successfully fits disability inception data.

Hybrid quantum-classical approach shows promise for insurance modeling.

Abstract

We propose a hybrid classical-quantum approach for modeling transition probabilities in health and disability insurance. The modeling of logistic disability inception probabilities is formulated as a support vector regression problem. Using a quantum feature map, the data is mapped to quantum states belonging to a quantum feature space, where the associated kernel is determined by the inner product between the quantum states. This quantum kernel can be efficiently estimated on a quantum computer. We conduct experiments on the IBM Yorktown quantum computer, fitting the model to disability inception data from a Swedish insurance company.