Neural Network Model of Pricing Health Care Insurance

TL;DR

This paper introduces a neural network model for health insurance pricing, aiming to improve prediction accuracy over traditional GAM models by leveraging deep learning techniques.

Contribution

The paper presents a novel neural network approach that outperforms GAM models in predicting health insurance costs, addressing limitations of existing statistical methods.

Findings

Neural network model achieves higher prediction accuracy than GAM.

The proposed method effectively captures complex health data patterns.

Neural network reduces prediction errors in health insurance pricing.

Abstract

To pricing health insurance plan, statisticians use mathematical models to predict customers' future health condition. General Addictive Model (GAM) is a wide accepted method for this problem. However, it have several limitations. To solve this problem, a new method named neural network model is implemented. Compare with GAM model, neural network provide a more accurate predicting result.