No abstract

As the usage of credit cards has become more common in healthcare application of everyday life, banks have found it very difficult to detect the credit card frauds systematically. The fraudulent activities should be identified and detected using new techniques. As a result, machine learning (ML) can help detect credit card fraud in transactions while also reducing the strain on financial institutions. This research aims to improve cybersecurity by detecting fraudulent transaction in data set using the new classifier strategies such as cluster & classifier based decision tree (CCDT), cluster & classifier based logistic regression (CCLR), and cluster & classifier based random forest (CCRF). The proposed strategies are applied to detect the healthcare fraudulent activities. This research implemented data analysis, pre-processing, and the deployment of these strategies to find the better results. The performance of the method is compared with other methods in terms of metrics and CCRF and CCLR perform better than other methods.

No abstract