- Every year, fraudulent transactions with credit cards result in billions of dollars in losses. The key to minimizing these losses is the development of effective fraud detection algorithms, and increasingly, these algorithms depend on cutting-edge machine learning methods to help fraud investigators. Nevertheless, because of the non-stationary distributions of the data, the extremely unbalanced classification distributions, and the ongoing streams of transactions, designing fraud detection algorithms is especially difficult. Due to confidentiality concerns, publicly available information are also hard to come by, leaving many questions regarding how to approach this problem in the dark.
-
A total of 127 million adults in America—or nearly half of the population—have experienced a fraudulent transaction on one of their credit or debit cards. Card fraud has happened more than once to more than one in three people who use credit or debit cards.
-
On American credit and debit cards, the typical charge was $62, which translates to around 8 billion in attempted fraudulent transactions. Only around 40% of cardholders have email or text notifications from their bank or credit card issuer activated.
-
Only 19% of victims with alerts turned on had to take further action to reverse fraudulent charges, compared to about 81 percent of victims without these warnings.
- Use an Address Verification System (AVS) to verify a cardholder's identity
- Verify the IP address of a customer
- Be wary of anonymous email addresses
- Ship only to the cardholder's billing address
- Analyze transaction data