Abstract:
As electronic commerce has gained widespread popularity, payments made for users' transactions through credit cards also gained an equal amount of reputation. Whenever shopping through the web is made, the chance for the occurrence of fraudulent activities are escalating. In this paper, we have proposed a three-phase scheme to detect fraudulent activities. A profile for the card users based on their behavior is created by employing a machine learning technique in the second phase extraction of a precise communicative pattern for the card users depending upon the accumulated transactions and the user's earlier transactions. A collection of classifiers are then trained based on all behavioral pattern. The trained collection of classifiers are then used to detect the fraudulent online activities that occurred. If an emerging transaction is fraudulent, feedback is taken, which resolves the drift's difficulty in the notion. Experiments performed indicated that the proposed scheme works better than other schemes.
Machine summary:
To prevent the consequences of fraudulent activities, it becomes very much essential to detect deceitful actions during credit card transactions (Van Vlasselaer, et al 2015 &Wei, Q.
3) Assignment of the trained classifier set to each card user in the collection as the behavioral pattern and the classifier having the utmost value is considered as the topical behavioral pattern We suggest a detection scheme for finding out the fraudulent activities in credit card usage, which employs a feedback mechanism to resolve the concept drift issue.
For training, machine learning-based methods utilized the basic transactional information and the features like accumulation plan, the importance of the application, amount of skew between the data, etc.
Whenever the algorithm detects fraud or classifies a transaction as a fraud, the system goes for the feedback mechanism, which uses a combination of the static and dynamic pin for the authentication and then it the user is authenticated, it updates the details of the current transaction in the records and updates the behavior profile.
A Novel Fraud Detection Scheme for Credit Card Usage Employing Random Forest Algorithm Combined with Feedback Mechanism.
A Novel Fraud Detection Scheme for Credit Card Usage Employing Random Forest Algorithm Combined with Feedback Mechanism.