Analysis of Discovering Fraud in Master Card Based on Bidirectional GRU and CNN Based Model

Detecting and confirming MasterCard fraud (also known as “master card fraud detection”) is a popular course topic amongst students due to the usefulness of data processing and machine learning strategies in combating cybercrime. The three main parts of the proposed method are preprocessing, feature extraction, and model training. Preprocessing techniques are used to mine crucial information for identifying MasterCard fraud. Only by using the most advanced and efficient algorithms, the future transactions can be predicted with any degree of certainty. By employing these techniques, the proposed approach may confirm a variety of facts, including the correctness of authentication and the regularity of dealings. To accomplish feature extraction, the proposed approach used the PCA and SKM algorithms. In order to train the models following feature extraction, the proposed approach uses CNN, BiGRU, and BiGRU-CNN. Both the CNN and the BiGRU models are outperformed by the proposed model. With an approximate 98.87 percent accuracy, the proposed method is superior to other methods such as CNN and BiGRU.