| Abstract |
The COVID-19 epidemic has restricted people's movement to some level, making it impossible to buy products and services offline, resulting in a culture of growing dependence on internet services. One of the most important concerns with using credit cards is fraud, which is especially difficult in the domain of online purchases. As a result, there is a critical need to discover the best strategy to employ data mining algorithms to prevent almost all fraudulent credit card transactions. So, the growth of information technology has led to a major number of databases and information in various fields. Many studies are being performed in order to change this important data for future use. The SMOTE technique was used for oversampling since the dataset was severely unbalanced. Furthermore, feature selection was performed, and the dataset was divided into two parts: training data and test data. The algorithm used in the experiment is Ada Boost (ADB). Results show that each algorithm can be used for credit card fraud detection with high accuracy. Proposed model can be used for the detection of other irregularities. |
