Online Transaction Fraud Detection using Backlogging on E-Commerce Website

Download Project Document/Synopsis

We here come up with a system to develop a website which has capability to restrict and block the transaction performing by attacker from genuine user’s credit card details. The system here is developed for the transactions higher than the customer’s current transaction limit. We tried to detect fraudulent transaction before transaction succeed. During registration we take required information which is efficient to detect fraudulent user activity. Here we present a Behavior and Location Analysis (BLA). The details of items purchased in Individual transactions are usually not known to any Fraud Detection System (FDS) running at the bank that issues credit cards to the cardholders. Hence, We implemented BLA for addressing this problem. An advantage to use BLA approach to reduce number of false positive transactions identified as malicious by an FDS although they are genuine. An FDS runs at a credit card issuing bank. Each incoming transaction is submitted to the FDS for verification. FDS receives the card details and transaction value to verify, whether the transaction is genuine or not. The types of goods that are bought in that transaction are not known to the FDS. Bank declines the transaction if FDS confirms the transaction to be fraud. User spending patterns and geographical location is used to verify the identity. If any unusual pattern is detected, the system requires re-verification. Based upon previous data of that user the system recognizes unusual patterns in the payment procedure. System will block the user after 3 invalid attempts.

  • The system is more secured with OTP (One Time Password) implementation.
  • IP address tracking at every transaction.
  • Security questions for payment limit crossed
  • More than 20-30 % deviation of user’s transaction (spending history and operating country) is considered as an invalid attempt and system takes action.

Leave a Comment

Your email address will not be published.