What is credit card Fraud ?? It can be defined as a case where a person uses someone else’s credit card for personal reasons while the owner and the card issuing authorities are unaware of the fact that the card is being used.

---

1-Research Paper

https://ieeexplore.ieee.org/abstract/document/4358713

As credit card is the most payment method being used for both online and regular purchase, and it is dramatically increases, the researcher suggest a model based on sequence of operations in credit card transaction using a hidden Markov model (HMM).

2-Research Paper

https://ieeexplore.ieee.org/abstract/document/4280163

According to this this research the credit card fraud has become rampant in recent years. the paper evaluate three classification methods (decision tree, neural networks and logistic regression).

3-Research Paper

https://www.sciencedirect.com/science/article/pii/S0167923610001326 The study mentioned that the use of data mining techniques for credit card fraud detection are relatively few,researcher use the support vector machines and random forests as part of his attempt to obtain better detection.

4-Research Paper

https://www.sciencedirect.com/

Application of Credit Card Fraud Detection: Based on Bagging Ensemble Classifier

the author suggest that the lack of credit card transactions data set for researcher is the reason of weak literature on credit card fraud,thr research indicate that Naïve Bayes (NB), Support Vector Machines (SVM), K-Nearest Neighbor algorithms (KNN) are the most common methods of such data model, and it finally suggest the bagging classifier based on decision three, as the best classifier for fraud detection, mainly for two reasons:

1. Performance is found to be more stable.
2. Bagging method takes very less time.

one of the top five fraud detection consultants revealed by topcreditcardprocessors.com on August 2013 ,shows that 40% of the total financial fraud is related to credit card and the loss of amount due to credit card fraud worldwide is .55 billion. There are various methods used for fraud detection each of them tries to increase the detection rate while keeping false alarm rate at minimum.

The research point to the below challenges in fraud detection

• Non-availability of real data set
• Unbalanced Data Set
• Size of the Data Set
• Determining the appropriate evaluation parameters
• Dynamic behavior of fraudster