JJEM: Special Edition 2 (December 2024)
JJEM: Special Edition 2 (December 2024)
2024-12-08
Detecting credit card fraud using machine learning and deep.
Tarun C L, Arunkumar K L
The internet gets utilized a lot more these days and has become a necessity in the modern world the simplicity and flexibility of purchasing and selling goods online has expanded along with e-commerce the advent of modern technologies such as online banking and credit card payments has led to a significant rise in the utilization of online shopping and bill having to pay the risk to utilizing a credit card increased as e-commerce and shopping became more popular this could be that credit cards were used in greater domains making it more difficult for any business related organizations to orient between legitimate and fraudulent transactions furthermore a disguise in the transaction may arise the prototype what we have been discussing shows how this study uses machine learning to detect fraud and block payments in real-time. It demonstrates how abnormalities may be found in an unsupervised way with greater accuracy. This anomaly detection approach has several uses, including identifying non-legal banking and overbilling in telecoms. security monitoring network traffic health care and a variety of manufacturing industries This work is a critical application of machine learning and neural networks, aimed at "detecting fraudulent activities. from a vast number of legitimate ones. However, one of the highest machine learning approaches such as logistic regression and Decision trees are often used Deep learning techniques. Credit card companies use machine learning to reduce false positives in fraud detection, Real-time fraud detection systems help prevent unauthorized credit card use.
Detecting fraud in credit cards, fraudulent transactions.