Credit cards fraud detection by negative selection algorithm on hadoop (To reduce the training time)

This paper proposed a model for credit card fraud detection system, which is aimed to improve the current risk management by adding an Artificial Immune System´s algorithm to fraud detection system. For achieving to this goal, we parallelize the negative selection algorithm on the cloud platform such as apache hadoop and mapreduce. The algorithm execute with three detectors set. The experiments show that by implement our fraud detection system on the cloud, the training time of algorithm in proportion to basic algorithm significantly decreases.