Healthcare Billing Fraud Detection Through Machine Learning And Using Homographic Encryption Technique For Prevention

Fraud on health care costs has become dangerous. The healthcare industry has focused on detecting and preventing fraud and increasing its focus on safety and security. Although much research has been done to resolve this issue, no standard solution has been adopted. Now the day app used to detect fraud is riddled with misconceptions and very false ideas. Machine learning allows the app to view locations based on data. The basis of previous self-awareness algorithms can be designed that allow the model to apply what it has learned from previous experiences. Machine learning tools are used to analyze fraudulent situations. Another important area we face in our project is the detection of fraud in real-time. We purpose to design a fraudulent detection model in this paper that provides us a large amount of efficiency, working with the kaggle fraud database. This novel idea is useful for predicting fraud less than 300 times, the current method will be phased with an accuracy of 99.62%, which can prevent many health billing security problems thus making the model more secure.