Credit Card Fraud Detection Using Hidden Markov Model-A Survey

Middle-East Journal of Scientific Research 20 (6): 697-699, 2014
ISSN 1990-9233
© IDOSI Publications, 2014
DOI: 10.5829/idosi.mejsr.2014.20.06.11387
Credit Card Fraud Detection Using Hidden Markov Model-A Survey
Nitu Kumari, S. Kannan and A. Muthukumaravel
Department of MCA, Bharath University,

Selaiyur, Chennai, 73, Tamil Nadu, India
Abstract: Due to a rapid advancement in the electronic commerce technology, the use of credit cards has
dramatically increased. As credit card becomes the most popular mode of payment for both online as well as
regular purchase, cases of fraud associated with it are also rising. In this paper, we model the sequence of
operations in credit card transaction processing using a Hidden Markov Model (HMM) and show how it can
be used for the detection of frauds. An HMM is initially trained with the normal behavior of a cardholder.
Key words: Electronic commerce technology Mode of payment Hidden Markov Model
INTRODUCTION Literature Survey: The feasibility of the project is

analyzed in this phase and business proposal is put forth
An HMM is initially trained with the normal behavior with a very general plan for the project and some cost
of a cardholder. If an incoming credit card transaction is estimates. During system analysis the feasibility study of
not accepted by the trained HMM with sufficiently high the proposed system is to be carried out [1-6]. This is to
probability, it is considered to be fraudulent. At the same ensure that the proposed system is not a burden to the
time, we try to ensure that genuine transactions are not company. For feasibility analysis, some understanding of
rejected. We present detailed experimental results to show the major requirements for the system is essential.
the effectiveness of our approach and compare it with
other techniques available in the literature. Three key considerations involved in the feasibility
analysis are:
Proposed System: Here we are introducing a project
for the credit card fraud detection using Hidden Economical Feasibility
Markov Model (HMM). It is done on the basis of the Technical Feasibility
spending profile of the card holder. The usual Social Feasibility
spending of the cardholder is being checked by the FDS
(Fraud Detection system) in the bank .The system checks Economical Feasibility: This study is carried out to check
all the spending of the user. When it turns unusual the the economic impact that the system will have on the
method blocks the transaction on the card [5]. And it organization. The amount of fund that the company can
alerts the bank. It occurs automatically. It doesn’t need pour into the research and development of the system is
any man power. limited [7]. The expenditures must be justified. Thus the
developed system as well within the budget and this was
The main advantage is that the detection occurs achieved because most of the technologies used are
much faster than any other method. freely available. Only the customized products had to be
In all the existing systems the real card holder should purchased.
checked for the Fraud detection. But in our method
there is no need of the physical inconveniences of Technical Feasibility: This study is carried out to check
the card holder. All the checking and the detection the technical feasibility, that is, the technical requirements
occur automatically. of the system. Any system developed must not have a
This project needs no man power for the detection. high demand on the available technical resources.
Corresponding Author: Nitu Kumari, Department of MCA, Bharath University, Selaiyur, Chennai, 73, Tamil Nadu, India.
697
Middle-East J. Sci. Res., 20 (6): 697-699, 2014
This will lead to high demands on the available technical Data Flow Diagram:
resources. This will lead to high demands being placed on
the client [8]. The developed system must have a modest
requirement, as only minimal or null changes are required
for implementing this system.
Social Feasibility: The aspect of study is to check

the level of acceptance of the system by the user.
This includes the process of training the user to use
the system efficiently. The user must not feel threatened
by the system, instead must accept it as a necessity.
The level of acceptance by the users solely depends on
the methods that are employed to educate the user about
the system and to make him familiar with it. His level of Register Module:
confidence must be raised so that he is also able to make
some constructive criticism, which is welcomed, as he is
the final user of the system [9].
Problem Solving: All the existing method to detect the

credit card was on the mode like the detection occurs only
after the complaint of the card holder about fraud done.
It is not a convenient way to avoid the loss happens to
the cad holder. After getting the complaint they detected
the fraud on the basis of the IP address. For this they
need the help of the Cyber crime to detect the fraud and
make action on it. It takes so much man power. Security Module
Module Description: Design is multi-step process that

focuses on data structure software architecture,
procedural details, (algorithms etc.) and interface between
modules. The design process also translates the
requirements into the presentation of software that can be
accessed for quality before coding begins.
Computer software design changes continuously as
new methods; better analysis and broader understanding
evolved. Software Design is at relatively early stage in its CONCLUSION
revolution [9].
Therefore, Software Design methodology lacks the This system has been developed as versatile and user
depth, flexibility and quantitative nature that are normally friendly. The performance of this project is proved to be
associated with more classical engineering disciplines. efficient. This project provides flexibility for incorporating
However techniques for software designs do exist, criteria new features, which may be necessary. Updating the
for design qualities are available and design notation can information is very important for each and every software
be applied. because every system is dynamic in nature. There is
certainly updating for even the website software because
Database Design: The database design is a must for any the new things maybe added and they have to be
application developed especially more for the data store modified for meeting the future requirements. Using the
projects. Since the chatting method involves storing the Visual Basic. NET concepts for the front-end and
message in the table and produced to the sender and SQL-Server 2005 as backend, the system will be modified
receiver. when required.
698
Middle-East J. Sci. Res., 20 (6): 697-699, 2014
Future Enhancement: The”CREDIT CARD FRAUD 5. Kerana Hanirex, D. and K.P. Kaliyamurthie, 2013.
DETECTION USING HIDDEN MARKOV MODEL”was Multi-classification approach for detecting thyroid
successfully designed. Every application has its own attacks, International Journal of Pharma and Bio
merits and demerits. The project has covered almost all Sciences, 4(3): B1246-B1251.
the requirements. Further requirements and improvements 6. Khanaa, V., K. Mohanta and T. Saravanan, 2013.
can easily be done since the coding is mainly structured Comparative study of uwb communications over fiber
or modular in nature. Changing the existing modules or using direct and external modulations, Indian Journal
adding new modules can append improvements. Further of Science and Technology, 6 (suppl 6): 4845- 4847.
enhancements can be made to the application, so that the 7. Kumar Giri, R. and M. Saikia, 2013. Multipath routing
web site functions very attractive and useful manner than for admission control and load balancing in wireless
the present one. mesh networks, International Review on Computers
and Software, 8(3): 779-785.
REFERENCES 8. Kumaravel, A. and K. Rangarajan, 2013. Routing
alogrithm over semi-regular tessellations, 2013 IEEE
1. ASP.NET Programming (Black Book) – Steven Conference on Information and Communication
Holzner. Technologies, ICT 2013.
2. ASP.NET Complete Reference – Jeffrey R. Shapiro. 9. Kumaravel, A. and K. Rangarajan, 2013. Algorithm for
3. SQL Server 7.0 – Stephen Wynkoop. automaton specification for exploring dynamic
4. SQL Server 2000 Complete Reference – Kevinloney labyrinths, Indian Journal of Science and
George Koch. Technology, 6(6).
699

Credit Card Fraud Detection Using Hidden Markov Model-A Survey

Uploaded by

Copyright:

Available Formats

Credit Card Fraud Detection Using Hidden Markov Model-A Survey

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Credit Card Fraud Detection Using Hidden Markov Model-A Survey

Uploaded by

Copyright:

Available Formats

Middle-East Journal of Scientific Research 20 (6): 697-699, 2014

Credit Card Fraud Detection Using Hidden Markov Model-A Survey

Nitu Kumari, S. Kannan and A. Muthukumaravel

Department of MCA, Bharath University,

INTRODUCTION Literature Survey: The feasibility of the project is

Social Feasibility: The aspect of study is to check

Problem Solving: All the existing method to detect the

Module Description: Design is multi-step process that

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.