METHOD FOR DETECTING FRAUDULENT CREDIT CARD TRANSACTIONS

Abstract

ABSTRACT A method (100) for detecting fraudulent credit card transactions. Further, the method (100) comprising pre-processing transaction data to handle missing values, outliers, and imbalanced datasets. Further, the method (100) comprising the steps of selecting at least one machine learning algorithm from a group consisting of supervised, unsupervised, and semi-supervised learning approaches. Further, the method (100) comprising the steps of evaluating the performance of the trained model using performance metrics including accuracy, precision, recall, and F1-score. Further, the method (100) comprising the steps of monitoring credit card transactions in real-time to identify suspicious activities. Further, the method (100) comprising the steps of generating alerts for transactions identified as suspicious to facilitate immediate action by fraud analysts. <>

Specification

Description:FIELD OF THE DISCLOSURE
[0001] This invention generally relates to the field of fraud detection systems and, in particular, to a method for identifying fraudulent activities in online credit card transactions, aimed at enhancing security and reducing financial losses for merchants and consumers.
BACKGROUND
[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] The rapid growth of e-commerce has led to an increase in online transactions, making credit card fraud a significant concern for both consumers and merchants. Traditional , Claims:1. A method (100) for detecting fraudulent credit card transactions, the method comprising the steps of:
pre-processing transaction data to handle missing values, outliers, and imbalanced datasets;
selecting at least one machine learning algorithm from a group consisting of supervised, unsupervised, and semi-supervised learning approaches;
evaluating the performance of the trained model using performance metrics including accuracy, precision, recall, and F1-score;
monitoring credit card transactions in real-time to identify suspicious activities; and
generating alerts for transactions identified as suspicious to facilitate immediate action by fraud analysts.

2. The method (100) as claimed in claim 1, wherein the pre-processing step includes applying under-sampling and oversampling techniques to balance the dataset, as well as performing feature engineering to identify relevant features indicative of fraud.

Documents