ABSTRACT

With the increasing popularity of Credit card usage, Credit Card fraud also increases. The number of online payment options has expanded thanks to e-commerce and several other websites, raising the possibility of online fraud. As a result, both people and financial institutions suffer significant losses. This research seeks to detect credit card fraud and make attempts to cut down on it. Financial institutions place a high priority on identifying and stopping fraudulent activity. Fraud prevention and detection are pricey, time-consuming, and labor-intensive processes. Several machine-learning algorithms can be utilized for detection. In order to evaluate past customer transaction information and identify behavioral traits, the study's main goal is to develop and apply a special fraud detection algorithm for simulcasting transaction data. Through the research, try to give a genuine solution to Credit card users and make their transactions secure. This research aims to propose a trustworthy and efficient way for identifying credit card fraud. The accuracy of several autonomous classifiers using machine learning that were employed for recognition is compared and examined. The Random Forest classifier has the highest accuracy of 99.98%.

Keywords: - Credit card fraud, Neural network, Random Forest, Imbalanced classification, Machine learning.