Cause and Effect Essay on Credit Cards - Special Academic Support

Do you need this or any other assignment done for you from scratch?

We assure you a quality paper that is 100% free from plagiarism and AI.

You can choose either format of your choice ( Apa, Mla, Havard, Chicago, or any other)

NB: We do not resell your papers. Upon ordering, we do an original paper exclusively for you.

NB: All your data is kept safe from the public.

Abstract

Fraud is any malicious activity that aims to cause financial loss to the other party. As the use of digital money or plastic money even in developing countries is on the rise so is the fraud associated with them. Frauds caused by Credit Cards have cost consumers and banks billions of dollars globally. Even after numerous mechanisms to stop fraud, fraudsters are continuously trying to find new ways and tricks to commit fraud. Thus, in order to stop these frauds we need a powerful fraud detection system that not only detects the fraud but also detects it before it takes place and in an accurate manner. We need to also make our systems learn from the past committed frauds and make them capable of adapting to future new methods of fraud.

In this paper, we have introduced the concept of fraud related to credit cards and their various types. We have explained various techniques available for a fraud detection system such as Support Vector Machine (SVM), Artificial Neural Networks (ANN), Bayesian Networks, K- Nearest Neighbour (KNN), Hidden Markov Models, Fuzzy Logic Systems, and Decision Trees.

An extensive review is done of the existing and proposed models for credit card fraud detection and a comparative study of these techniques on the basis of quantitative measurements such as accuracy, detection rate, and false alarm rate. The conclusion of our study explains the drawbacks of existing models and provides a better solution in order to overcome them.

Keywords: Neural Network, Genetic Algorithm, Support Vector Machine, Bayesian Network, K- Nearest Neighbour, Hidden Markov Model, Fuzzy Logic Based System, Decision Trees.

I. Introduction

Today the use of Credit cards even in developing countries has become a common scenario. People use it to shop, pay bills, and for online transactions. But with an increase in the number of Credit Card users, the cases of fraud in Credit cards have also been on the rise. Credit Card-related frauds cause global loss of billions of dollars. Fraud can be classified as any activity with the intent of deception to obtain financial gain in any manner without the knowledge of the cardholder and the issuer bank. Credit Card fraud can be done in numerous ways. By lost or stolen cards, producing fake or counterfeit cards, cloning the original site, erasing or modifying the magnetic strip present on the card that contains the users information, phishing, skimming, or stealing data from a merchants side.

Fraud detection deals with finding a fraud activity amongst thousands of genuine ones, which in fact puts forward a challenge. With continued advancement in fraudulent strategies, it is important to develop effective models to combat these frauds in their initial stage only, before they can take to completion. However, the major challenge in developing such a model is that the number of fraudulent transactions among the total number of transactions is a very small number and hence the work of finding a fraudulent transaction in an effective and efficient way is quite bothersome.

II. Literature survey

In 2015, J. Esmaily and R. Moradinezhad in their paper proposed a hybrid of artificial neural networks and decision trees. In their model, they used a two-phase approach. In the first phase, the classification results of the Decision tree and Multilayer perceptron were used to generate a new dataset which in the second phase is fed into the Multilayer perceptron to finally classify the data. This model promises reliability by giving a very low false detection rate. Siddhartha Bhattacharyya and 4 others in their paper in 2011 did a detailed comparative study of Support vector machine and random forest along with logistic regression. They concluded through experiments that the Random Forest technique shows the most accuracy followed by Logistic Regression and Support Vector Machine. Raghavendra Patidar and Lokesh Sharma in 2011 proposed a hybrid of Artificial Neural Network and Genetic Algorithm in their paper. They used a neural network to classify the transactions and a genetic algorithm to optimize the solution and not over-train the system. In 2015, Tanmay Kumar and Suvasini Panigrahi in their paper proposed a hybrid approach to credit card fraud detection using fuzzy clustering and a neural network. It makes use of two phases. In phase one, they used a c-means clustering algorithm to generate a suspicious score of the transaction and in the next phase, if a transaction is suspicious it is fed into a neural network to determine whether it was really fraudulent or not.

III. Proposed system

The proposed fraud detection model is outlined in Figure. During the training phase, the legal transaction pattern and fraud transaction pattern of each customer is created from their legal transactions and fraud transactions, respectively, by using frequent item set mining. Then during the testing phase, the matching algorithm detects to which pattern the incoming transaction matches more.

IV. Conclusion

Although there are several fraud detection techniques available today none is able to detect all frauds completely when they are actually happening, they usually detect it after the fraud has been committed. This happens because a very minuscule number of transactions from the total transactions are actually fraudulent in nature. So we need a technology that can detect the fraudulent transaction when it is taking place so that it can be stopped then and there and that too at a minimum cost. So the major task of today is to build an accurate, precise, and fast fraud detection system for credit card frauds that can detect not only frauds happening over the internet like phishing and site cloning but also tampering with the credit card itself i.e. it signals an alarm when the tampered credit card is being used.

III. References

E. D. Yusuf Sahin, Detecting credit card fraud by logistic regression, 2011.
T. R. C. Sudha, Credit card fraud detection in internet using k nearest neighbor algorithm, IPASJ international journal of computer science, vol. 5, no. 11, 2017.
A. A. Pansy Khurana, Credit card fraud detection using fuzzy logic and neural network, Spring Sim, 2016.
D. L. G. S. Chandrahas Mishra, Credit card fraud detection using neural networks, International Journal of Computer Science, vol. 4, no. 7, July 2017.
A. A. Nancy Demla, Credit card fraud detection using reduction of false alarms, International Journal of Innovations in Engineering and Technology, vol. 7, no. 2, 2016.

Click Here To Order Now!