Credit card fraud is an event problem and fraud
detecting techniques getting more sophisticated each day. Mainly
internet is becoming more common in almost every domain.
Online transactions, shopping, and e-commerce are expanding
step by step. Due to which in the online payment system,
fraudulent activities have also increased. It has cost banks and
their customers a loss of billions of rupees. The techniques used
now a day detects the anomaly only after the fraud transaction
takes place. The intruders have found ways to crack the system
loopholes and defeat the security. These frauds are not consistent
in their actions, they constantly alter. Thus, Artificial Intelligent
(AI) algorithms are used to detect the behavior of such activity by
learning the past behavior of the transaction of the users. An
unsupervised algorithm is used to detect online transactions, as
fraudsters commit fraud once by online media and then move on
to other techniques. This paper discusses the performance
analysis and the comparative study of the two Deep Learning
algorithms which include auto-encoder and the neural network.
In this paper accuracy, precision, recall, and AUC curve are
considered as a model evaluation factor.