Credit Card Fraud Detection Using Learning to Rank Approach
N. Kalaiselvi, S Rajalakshmi, J. Padmavathi, Joyce. B. Karthiga · 2018
An infrastructure build in the neural network platform is reliable to detect the fraudulence in credit card system for transaction. The issues resulting from the fraud in credit card transaction may involve a number of customers who drift their habits evolve and fraudsters who change their strategies over time. The vast majority of learning algorithms that have been proposed for fraud detection rely on assumptions that hardly hold in a real-world fraud-detection system. This includes the classification of data imbalance which is used to verify their hidden transaction, track the location of the fraudsters and to capture their image. The implementation of learning algorithm will precisely predict and rank alerts based on the scores allotted to each alert. Initially, we propose transaction blocking rule to ensure the security of the transaction. Secondly, we design scoring rules that involve pattern matching based on frequent data mining techniques. Finally, the machine is trained and updated with the dataset to timely investigate the transaction thereby earning credit card holder's satisfaction.