Paper Contents
Abstract
Health insurance is a crucial choice when it comes to ensuring a secure future. The insurance industry plays a significant role in fostering sustainable economic development in every nation. Fraud including health insurance claims, is a prevalent issue within the financial sector. This study focuses on analysing health insurance claims to detect and anticipate potential fraud. To achieve this, feature selection improve the performance of the model and eliminating irrelevant feature. The comparison between CatBoost and Light GBM showed that the CatBoost model is better than the Light GBM. Based on the result of accuracy, precision, recall and F1-score values on both models
Copyright
Copyright © 2024 Pooraniarul P. This is an open access article distributed under the Creative Commons Attribution License.
