A Machine and Deep Learning Framework for Robust Health Insurance Fraud Detection and Prevention DOI Open Access

Suhag Pandya

International Journal of Advanced Research in Science Communication and Technology, Год журнала: 2023, Номер unknown, С. 1332 - 1342

Опубликована: Июль 30, 2023

Healthcare fraud is the deliberate submission of false information or fabrication facts in order to get entitlement payments. As a result, it wastes healthcare funds and raises expenses. For both insurance firms consumers, predicting health prices an essential undertaking. The purpose this research examine feasibility using ML models for accurate identification medical fraud. Using dataset with more than 1300 entries important characteristics such charges, smoking status, geography, BMI, age, sex, children, investigates use ANN strong detection. Traditional like Ridge, Lasso, XGBoost fared poorly when compared ANN, which achieved R² 92.72 low RMSE 0.27, according error measures utilised assess model's performance. A findings show that good at identifying fraudulent claims, bodes well its future better prevention systems. Limitations include dataset's small size limited features, suggesting studies should expand explore advanced techniques further optimisation

Язык: Английский

Self-Learning Neural Networks in the Cloud: Towards Autonomous AI Systems DOI
Godwin Olaoye

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A Machine and Deep Learning Framework for Robust Health Insurance Fraud Detection and Prevention DOI Open Access

Suhag Pandya

International Journal of Advanced Research in Science Communication and Technology, Год журнала: 2023, Номер unknown, С. 1332 - 1342

Опубликована: Июль 30, 2023

Healthcare fraud is the deliberate submission of false information or fabrication facts in order to get entitlement payments. As a result, it wastes healthcare funds and raises expenses. For both insurance firms consumers, predicting health prices an essential undertaking. The purpose this research examine feasibility using ML models for accurate identification medical fraud. Using dataset with more than 1300 entries important characteristics such charges, smoking status, geography, BMI, age, sex, children, investigates use ANN strong detection. Traditional like Ridge, Lasso, XGBoost fared poorly when compared ANN, which achieved R² 92.72 low RMSE 0.27, according error measures utilised assess model's performance. A findings show that good at identifying fraudulent claims, bodes well its future better prevention systems. Limitations include dataset's small size limited features, suggesting studies should expand explore advanced techniques further optimisation

Язык: Английский

Процитировано

2