Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 11 (2022) > Article

DOI: 10.14704/nq.2022.20.11.NQ66190


Govind Prasad Buddha,Dr. NAGAMALLESWARA RAO


The expansion of online purchases is a direct outcome of the rise of e-commerce, which in turn has spawned a wide range of safety concerns. Even while there are always potential security risks when using any human-created technology, online or electronic payment systems provide the highest level of protection possible. Since e-payments are so convenient, they are attractive to both merchants and consumers. As a result, there is an urgent need for efficient tools to counteract the risks posed by the internet. The use of credit and debit cards is one of the most prevalent forms of electronic commerce that is vulnerable to these dangers. Stopping credit card fraud has consistently ranked towards the top of banks' lists of security concerns. There are numerous methods used in credit card fraud. The ability to identify and stop such scams is one of today's most pressing concerns. Due to the rise in online fraud, scientists have turned to a variety of machine learning techniques to help them identify and analyse instances of online theft. The primary goal of this work is to provide a brand-new fraud detection approach for Streaming Transaction Data by analysing customers' past financial dealings and drawing conclusions about their habits based on what they learn. Methods that rely on rules-based approaches or classic point solutions are out of date. For banks and other financial services institutions, the time and money spent by legal and compliance departments attempting to overcome these roadblocks is prohibitive. Advanced analytics, as well as AI and ML capabilities, free up fraud and compliance teams to focus on the most difficult cases. Complex algorithms powered by ML can lessen the need for manual investigation; when used in tandem with rules, this approach to fraud detection has considerable advantages over rule-based systems alone. In this paper, we compare and contrast the various machine learning algorithms that are currently in use for credit card fraud detection.


Credit card, Fraud, Machine Learning.

Full Text