You are on page 1of 3

Volume: 03, Issue: 02, December 2014

Pages: 398-400

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

A Comparative Analysis on Credit Card


Fraud Techniques Using Data Mining
T.Abdul Razak1 , G.Najeeb Ahmed2
1

Associate Professor, Department of Computer Science, Jamal Mohamed College, Tiruchirapalli


2Research Scholar, Research & Development, Bharathiar University

ABSTRACT
Credit Card has become increased in recent years. In current world the fraud is one of the major issue of
financial transactions. It is important to understand the mechanism of executing a fraud. Fraud detection
includes monitoring of the spending behavior of customers. As credit card becomes the mode of payment for
both online as well as regular purchase. The use of credit card is common in modern day society. It is very
important to prevent unauthorized access to system resources and data. To build a completely secure system, in
addition with the authentication process behavior analysis also required, prior to completing a transaction.
Modern techniques based on Data mining Machine learning, Artificial Neural Network etc., has been introduced
for detecting credit card fraudulent transactions.
1.

INTRODUCTION

Data mining uses Data Analysis tools to discover


unknown, hidden and valid patterns as well as
relationships in large data sets. Data mining tools
include mathematical algorithms, statistical
models, and machine learning methods such as
algorithms
which
improve
performance
automatically through learning such as Neural
Networks and Decision Trees. Data Mining
consists of collection and management, analysis
and prediction of corresponding data sets. Data
mining can be performed on data sets represented
in quantitative, textual or multimedia forms. On the
other hand, Data mining applications can use a
range of parameters to observe the data. Data
mining applications include association rules,
classification methods, clustering and forecasting
as well. Detecting Credit Card fraud is a difficult
task when using normal procedures so the
development of the credit card fraud has become
more significance. The term fraud here refers to the
abuse of a profit organizations system without
necessarily leading to direct legal consequences.
Fraud detection is a continuously evolving
discipline and ever changing tactics to commit
fraud. Fraud is an adaptive crime and it is
increasing every year. So it needs special methods
of intelligent data analysis to detect and prevent it.
Classification and prediction are two forms of data
analysis that can be used to extract models. Many
classification and prediction methods have been
proposed by researchers in Data Mining. Credit
card fraud has been expanding issue in the credit
card industry. Detecting credit card fraud is a
difficult task when using normal process, so the
development of the credit card fraud detection
models has become of importance whether in the
academic or business organizations. A number of
Integrated Intelligent Research (IIR)

systems/models, process and preventive measures


will help to stop credit card fraud and reduce
financial risks. Banks and credit card companies
have gathered large amounts of credit card account
transactions.
RELATED WORK
From the work of view for preventing credit card
fraud, more research works were carried out with
special emphasis on data mining and neural
networks.
Sam and Karl suggest a credit card fraud detection
system using Bayesian and neural network
techniques to learn models of fraudulent credit card
transactions. Kim and Kim have identified skewed
distribution of data and mix of Legitimate and
fraudulent transactions as the two main reasons for
the complexity of credit card fraud detection .This
paper investigates the usefulness of applying
different learning approaches.
Some of the examples of such algorithms include
BAYES (Clark and Niblett, 1989). Prodromidis
and Stolfo use an agent-based approach with
distributed learning for detecting frauds in credit
card transactions. It is based on artificial
intelligence and combines inductive learning
algorithms and metalearning methods for achieving
higher accuracy.
METHODOLOGY
I. Neural Networks
A Neural Network (NN) is a collection of
processing nodes transferring activity to each
other via connections. Neural Networks (NN) have
been successfully applied in a broad range of
supervised and unsupervised learning applications.
Neural Network (NN) learning algorithms that are

398

Volume: 03, Issue: 02, December 2014


Pages: 398-400

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

capable to form logical models and that do not


nonlinear mapping relation from the input space to
output space, Neural Networks (NN) can learn
from the given cases and then summarize the
internal principles of data even without knowing
the potential data principles. On the other side,
Neural Network (NN) can easily familiarize its
own behavior to the new environment with the
corresponding results of formation of general
capability of evolution from present situation to the
new environment.
In this approach, NN use multi-layer neural
network model and Back Propagation (BP)
algorithm) runs on the network. Back Propagation
learns by iteratively processing a data set of
training tuples comparing the networks prediction
for each tuple with the real known target value.
Weights are modified so as to minimize the mean
squared error between the networks prediction and
the actual target value for every training tuple.
These modifications are made in the backwards
direction, that is, from the output layer through
each hidden layer down to the first hidden layer.
ANN (Artificial Neural Network) refers to a group
of non-linear, statistical modeling techniques
derived from the structure of the human brain.
ANN can be used in modeling of any complex
transactional pattern such that they are well suited
to the credit card fraud detection problem . Basic
element of a Neural Network (NN) is a neuron
which accepts many inputs, sums them, applies a
transfer function and then generates corresponding
result either as a model prediction or as input to
other neurons. A Neural Network is a structure of
many neurons connected in a regular way. The
most well-known Neural Networks used are FeedForward Neural Networks (FFNN), which is also
known as multilayer perceptrons.
Neural Network as a Classifier
However, Neural Network (NN) when seen as a
classifier has some weaknesses and strength as
well. Neural Network (NN)
Weakness involves:
(a) Long training time
(b) Require a number of parameters typically best
determined empirically, that is the network
topology.
(c) Poor interpretability: Difficult to understand the
symbolic meaning behind the learned weights and
of ``hidden units" exists in the network.
NN has its own strengths:
(a) High tolerance to noisy data
(b)Ability to classify untrained patterns
(c)Successful on a wide array of real-world data

Integrated Intelligent Research (IIR)

(d) Well-suited for continuous-valued inputs and


outputs.
(e)Algorithms are inherently parallel
(f)Techniques have recently been developed for the
extraction of rules from trained neural networks.

Fig : Framework for Nerual Network


II. MACHINE LEARNING
Machine Learning has the ability of a program to
learn from experience that is, to modify its
execution on the basis of newly acquired
information. The ability of a machine is to improve
its performance based on previous results. Fraud is
an adaptive crime which needs special methods of
intelligent data analysis to detect and prevent it.
Types of fraud

Credit card fraud

Insurance claim fraud

Mobile / cell phone fraud

Insider trading

Fraud Detection, is concerned with the detection of


fraud cases from logged data of system and user
behavior.
Data mining and Machine Learning is a relatively
new technique that is proving to be extremely
effective in detecting fraud, and it offers insurers
new opportunities to reduce losses.
There are many types of machine learning
1. Supervised Learning: in which the data is
labeled with the correct answers. The two most
common types of supervised learning is
Classification and Regression. example of a
classification problem is for the computer to learn
how to recognize handwritten digit, Supervised
learning can also be used in medical diagnoses for
instance, given a set of attributes about potential
cancer patients, and whether those patients actually
399

Volume: 03, Issue: 02, December 2014


Pages: 398-400

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

had cancer, the computer could learn how to


distinguish between likely cancer patients and
possible false alarms.

[6] Mirjana Pejic-Bach, Profiling intelligent


systems applications in fraud detection and
prevention: survey of research articles, 2010

2. Unsupervised Learning: in which are given a


collection of unlabeled data, which we wish to
analyze and discover patterns within dimension
reduction and clustering. The goal is to have
computer learn how to do something that we dont
tell it how to do!Clustering can be useful when
there is enough data to form clusters (though this
turns out to be difficult at times) and especially
when additional data about members of a cluster
can be used to produce further results due to
dependencies in the data.

International Conference on Intelligent Systems,


Modeling and Simulation.

3. Reinforcement Learning: in which an agent


seeks to learn the optimal actions to take based on
the past actions e.g. Robot
CONCLUSION & FUTURE WORK
Credit card fraud has become more and more
rampant in recent years. To improve merchants
risk management level in an automatic and
effective way, building an accurate and easy
handling credit card risk monitoring system is one
of the key tasks for the merchant banks. One aim of
this paper is to identify the user model with best
identifies fraud cases. It is possible to use Bayesian
Networks based on the input representation method
and the developed clustering model in the real
fraud detection system. In the future, these models
can extend to use in health insurance fraud
detection.

[7] Prabin Kumar Panigrahi, A Framework for


Discovering Internal Financial Fraud using
Analytics,
International
Conference
on
Communication
Systems
and
Network
Technologies 2011
[8] Raghavendra Patidar, Lokesh Sharma, Credit
Card Fraud Detection Using Neural Network,
International Journal of Soft Computing and
Engineering (IJSCE) ISSN: 2231-2307, Volume-1,
Issue-NCAI2011, June 2011.
[9] 1S. Benson Edwin Raj, 2A. Annie Portia
Analysis on Credit Card Fraud Detection Methods
ICCCET2011, 18th & 19th March, 2011 978-14244-9394-4/11/$26.00 2011 IEEE] 152
[10] Sahin, Y., Duman, E.: An overview of
business domains where fraud can take place, and a
survey of various fraud detection techniques.
In:Proceedings of the 1st International Symposium
on Computing in Science and Engineering, Aydin,
Turkey (2010).
[11] Tej Paul Bhatla, Vikram Prabhu & Amit Dua
Understanding Credit Card Frauds, 2003.
[12] V. Filippov L. Mukhanov B. Shchukin Credit
Card Fraud Detection System.

REFERENCES

[13] Y. Sahin, E. Duman Detecting Credit Card


Fraud by ANN and Logistic Regression 2011.

1. A. Shen, R. Tong, and Y. Deng, "Application of


classification models on credit card fraud
detection," June 2007.

13 Network, Proceedings of the International


Conference on SystemScience, pp. 621-630, 1994

2. Brause, R., Langsdorf, T. and Hepp, M. (1999).


Neural data mining for credit card fraud detection
Proceedings 11th IEEE International Conference
on Tools with Artificial Intelligence.TAO GUO,
GUI-YANG LI, NEURAL DATA MINING FOR
CREDIT CARD FRAUD DETECTION 978-14244-2096-4/08 2008 IEEE, 3630, July 2008.
[3] Chen, R.-C., Luo, S.-T., Liang, X., Lee, V. C.
S.: Personalized approach based on SVM and ANN
for detecting credit card fraud. In:

[14] Aleskerov, B. Freisleben, B. Rao,


CARDWATCH: A Neural Network Based
Database Mining System for Credit Card Fraud
Detection, Proceedings of IEEE/IAFE Conference
onComputational Intelligence for Financial
Engineering (CIFEr), pp.220-226, 1997
[15] M. Syeda, Y.Q. Zhang, Y. Pan, Parallel
Granular Neural Networks for Fast Credit Card
Fraud Detection, Proceedings of the IEEE
International Conference on Fuzzy Systems, pp.
572-577, 2002.

Proceedings of the IEEE International Conference


on Neural Networks and Brain, Beijing, China
(2005).
[4] Dahl, J.: Card Fraud. In: Credit Union
Magazine (2006).
[5] Dorronsoro, Ginel, Sgnchez and Cruz. Neural
fraud detection in credit card operations. Neural
Networks, IEEE Transactions. Volume: 8,Issue: 4:
827-834, 1997.

Integrated Intelligent Research (IIR)

400