Geo-location based credit card fraud detection

• Main Author: Lee, Boon Peng
• Other Authors: Sinha Sharad
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: http://hdl.handle.net/10356/74041
• Institution: Nanyang Technological University

The use of credit card is prevalent, and will continuously increase. Although EMV (Europay, MasterCard, and Visa) chips is one such alternative to prevent credit card fraud, experts predict that credit card fraud will continue to rise in numbers. Most of the current credit card fraud detection utilizes Machine Learning and/or Artificial Intelligence, but these fraud detection tasks are done by credit card companies, who handles and intercept fraudulent transaction, which customers have no control over, since user cannot view their own transactions to detect fraud. Although there exist applications that allow user to view their transactions, most of them do not tell the location of these transactions and neither is there an application that allows users to detect fraudulent transactions at their end. Often, it is too late before a user may notice such transactions based on credit card statement. This project aims to create a web application that allows users to enter their credit card transaction details, having all transactions to be pinpointed to the map with details using Google Maps, and then identifying outliers within the clusters of transactions using Density Based Spatial Clustering Algorithm with Noise (DBSCAN). This application aims to allow user to have a better view of transaction details on the map and granting the user more control over these transactions.