ABSTRACT:

Fraud has become a trillion-dollar industry today. Some finance companies have separate domain expert teams and data scientists who are working on identifying fraudulent activities. Data Scientists often use complex statistical models to identify frauds. However, there are many disadvantages to this approach. Fraud detection is not real-time and therefore, in many cases fraudulent activities are identified only after the actual fraud has happened. These methodologies are prone to human errors. In addition, it requires expensive, highly skilled domain expert teams and data scientists. Nevertheless, the accuracy of manual fraud detection methodologies is low and due to that, it is very difficult to handle large volumes of data. More often, it requires time-consuming investigations into the other transactions related to the fraudulent activity in order to identify fraudulent activity patterns.

Introduction:

Credit card is the commonly used payment mode in the recent years. As the technology is developing, the number of fraud cases are also increasing and finally poses the need to develop a fraud detection algorithm to accurately find and eradicate the fraudulent activities. Credit card is a small thin plastic or fiber card that contains information about the person such as picture or signature and person named on it to charge purchases and service to his linked account charges for which will be debited regularly. Now a days card information is read by ATMs, swiping machines, store readers, bank and online transaction. Each card as a unique card number which is very important, its security is mainly relies on physical security of the card and also privacy of the credit card number.There is rapid increase in the credit card transaction which as led to substantial growth in fraudulent cases. Many data mining and statistical methods are used to detect fraud. Many fraud detection techniques are implemented using artificial intelligence, pattern matching. Detection of fraud using efficient and secure methods are very important.
Credit card frauds are increasing heavily because of fraud financial loss is increasing drastically. Now days Internet or online transaction growing as new technology are coming day by day. In these transaction Credit card holds the maximum share. In 2018 Credit card fraud losses in London estimated US dollar 844.8 million. To reduce these losses prevention or detection of fraud must be done. There are different types of frauds occurring as technology is growing rapidly. So there are many machine algorithms are used to detect fraud now days hybrid algorithms, artificial neural network is used as it gives better performance