Credit Card Fraud Detection with a Neural-Network
نویسندگان
چکیده
Using data from a credit card issuer, a neural network based fraud detection system was trained on a large sample of labelled credit card account transactions and tested on a holdout data set that consisted of all account activity over a subsequent two-month period of time. The neural network was trained on examples of fraud due to lost cards, stolen cards, application fraud, counterfeit fraud, mail-order fraud and NRI (non-received issue) fraud. The network detected significantly more fraud accounts (an order of magnitude more) with significantly fewer false positives (reduced by a factor of 20) over rulebased fraud detection procedures. We discuss the performance of the network on this data set in terms of detection accuracy and earliness of fraud detection. The system has been installed on an IBM 3090 at Mellon Bank and is currently in use for fraud detection on that bank’s cmlit card portfolio. Credit Card Fraud Problem Credit card fraud is a growing problem in the credit card industry. In the US alone, losses from all types of credit card fraud are projected to exceed $850 million, representing a 10% increase in fraud losses over 1991 111. Though small when compared to credit card losses due to charge-offs of seriously delinquent accounts (charge-offs accounted for $8.5 billion of losses in 1992). fraud represents an increasing percentage of total charge volume, indicating that it is growing faster than the credit card business itself. From 1988 through 1991, the size of the fraud problem grew from 8 basis points to over 20. Although credit card fraud takes many forms, there are several principal categories. Fraud due to lost cards and stolen cards generally accounts for a certain “base level” of fraud activity. The size of this base level can be affected by general economic conditions (e.g., times of high unemployment are correlated with increases in fraud losses due to lost 1060-3425/94 $3.00
منابع مشابه
Credit Card Fraud Detection using Data mining and Statistical Methods
Due to today’s advancement in technology and businesses, fraud detection has become a critical component of financial transactions. Considering vast amounts of data in large datasets, it becomes more difficult to detect fraud transactions manually. In this research, we propose a combined method using both data mining and statistical tasks, utilizing feature selection, resampling and cost-...
متن کاملEnsemble Classification and Extended Feature Selection for Credit Card Fraud Detection
Due to the rise of technology, the possibility of fraud in different areas such as banking has been increased. Credit card fraud is a crucial problem in banking and its danger is over increasing. This paper proposes an advanced data mining method, considering both feature selection and decision cost for accuracy enhancement of credit card fraud detection. After selecting the best and most effec...
متن کاملA Revived Survey of Various Credit Card Fraud Detection Techniques
As there is a vast advancement in the E-commerce technology, the use of credit cards has grown up. The credit card has become the crucial mode of payment so with the rise in the credit card transactions, the credit card frauds have also become frequent nowadays. [1] Thus, an improved fraud detection system has become essential to maintain the reliability of the payment system. The criterion is ...
متن کاملCredit Card Fraud Detection by Adaptive Neural Data Mining
The prevention of credit card fraud is an important application for prediction techniques. One major obstacle for using neural network training techniques is the high necessary diagnostic quality: Since only one financial transaction of a thousand is invalid no prediction success less than 99.9% is acceptable. Due to these credit card transaction proportions complete new concepts had to be deve...
متن کاملCredit Card Fraud Detection with a Cascade Artificial Neural Network and Imperialist Competitive Algorithm
Credit Card Fraud is one of the biggest threats to business establishments today. This paper presents a cascade artificial neural network for the recognition of credit card fraud detection. This system aims at attaining a very high recognition rate and a very high reliability, In other words, excellent recognition performance of credit card fraud detection was obtained. Then, One solution was p...
متن کامل