Credit card fraud detection using machine learning

Author

Nyamutsamba, Chipo T.

Title

Credit card fraud detection using machine learning

Abstract

Fraudsters steal a lot of money every day, so it's critical to develop algorithms that can
help cut down on these losses. However, due to the non-stationary distribution of the
data, the extremely imbalanced class distributions, and the availability of few
transactions tagged by fraud investigators, the construction of fraud detection
algorithms is particularly difficult. The optimal course of action is unclear because there
is a lack of publicly available information due to confidentiality concerns. To produce
reliable alerts, detection systems must be able to handle the demands of real-world
operations and incorporate feedback from researchers. The most widely used payment
methods both online and offline are credit cards. The increased use of credit cards
globally is also leading to an increase in fraud.
Every store in the world accepts credit cards for cashless transactions. A fraudulent
transaction will be discovered after it has been completed by the credit card fraud
detection system. To identify, examine, and stop credit card fraud, several methods
have been created. Examples of these include machine learning algorithms and
techniques, big data analytics, and artificial neural networks. The objective of this study
is to forecast the incidence of fraud utilizing machine learning methods and algorithms
including Logistic Regression.

Date

2023

Publisher

BUSE

Keywords

Artificial neural networks

Credit card fraud detection

Fraud detection

Big data analytics

Machine learning

Supervisor

Mr Muzurura