• Version
• Download 16
• File Size 409.77 KB
• File Count 1
• Create Date 28 May 2023
• Last Updated 28 May 2023

CREDIT CARD FRAUD DETECTION

Anjali Sharma , Md.Atif Ahmad, Tanisha Agarwal

Rohit Aggarwal

rohitaggarwal@gmail.com

anjali.sharma.csit.2019@miet.ac.in,tanisha.agarwal.csit.2019@miet.ac.in,aatif.ahmad.csit.2019@miet.ac.in

Computer Science and Information Technology

Meerut Institute of Engineering and Technology, Meerut, India

Abstract - In order to protect our clients from being paid for services they did not request, we have implemented the following policy; credit card issuers need a way to detect fraudulent credit card transactions. Using data science and machine learning together, we can find solutions to these issues. In this research, machine learning is modelled for a data collection using credit card fraud detection. To model earlier credit card transactions using information from those that turned out to be fraudulent, a solution to the credit card fraud detection problem must be found. The chance of a new transaction being fraudulent is then calculated using this model. Our key objective in this instance is to find all fraudulent transactions while also lowering the number of false positives for fraud. This methodology relied on data analysis, preprocessing, and anomaly identification methods including the Local Outlier Factor and the Isolation Forest algorithm on PCA-transformed Credit Card Transaction data.

Keywords-– Automated fraud detection, isolation forest method, local outlier factor, applications of machine learning, and data science.