Banking Fraud Detection Using Machine Learning Algorithms
Upagna Rao Balasankula, Bonthu Poojitha, Sravanthi Chekurtha, Kruthika Buyya, Harika Bala, Punna Rao V · 2024
As technology grows rapidly, new innovations have emerged in our generation. Unfortunately, the rate of fraudulent activities has also increased, and as a result great deal of innocent individuals are in misery. Prior to the internet revolutionizing the world, banks employed traditional methods, including manual reviews, data analytics, transaction monitoring in reporting suspicious activities. However, as technology advances, bank fraud cases continue to rise. Banks must use caution when looking for banking system fraud. This project aims to adapt to these technological changes, detect abnormal behaviors in the dataset, and improve the overall performance of the trained model to protect against evolving malpractices. Combining Machine learning algorithms such as logistic regression and random forest results in improve the performance of these systems which gives significant result in detecting the fraudulent activities. Implementing these technologies will improve overall security, speed up response time, and improve accuracy by recognizing suspicious activity. In conclusion, using AI technologies, specifically machine learning helps banks stay one step ahead of fraudsters, by recognizing the need of early detection of malpractice, the study can prevent such tragedies from happening in the future.