You are on page 1of 5

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882

Volume 4, Issue 11, November 2015

AN EFFICIENT APPROACH FOR IDENTIFYING FRAUD


TRANSACTIONS ON E-COMMERCE DATA
D.Srikanth[1], N.Zareena[2]
1

M.Tech Scholar, Department of Computer science,


Vignans Lara Institute of Technology and science, Vadlamudi, India
2
M.Tech, Assistant Professor, Department of Computer science,
Vignans Lara Institute of Technology and science, Vadlamudi, India

ABSTRACT
Privacy preserving is one of the most critical research
topics in the data security garden and it has become a
serious burden in the secure transformation of personal
data in later years. Number of algorithmic techniques has
been devise for Privacy Preserving Data Mining
(PPDM). For example, different credit card concourse
may try to build better data sharing portrait for credit
card fraud exposure through PPDA tasks. Although
certain PPDA techniques collateral that nothing other
than the final analysis result is concede, it is impossible
to establish whether or not participating affair are
truthful about their private input data. This increment the
question of how to design impetus compatible privacyconserve data analysis techniques that excite
participating parties to afford truthful input data. A
model has been expected to design the adequate
incentive consistent model for secure private information
transformation and determine the fraud transactions
using genetic design. Every user need to transform the
exclusive data in many applications (E-Shopping) that
must be covered from the hackers. Building this model
confide in on many privacy preserving data mining
facility like Cryptographic techniques, Privacy
preserving association order and Function Evaluation
Theorem. The Incentive model is very efficient for
isolation preserving data mining, because it provides the
protocols contra not only semi-honest competitor model
and also the malignant model and we proposes identifies
the extortion transactions occupying on the users
transactions knowledge.
Key Words: Electronic commerce, fraud, credit card,
ancestral algorithms, detection.

1. INTRODUCTION
Data mining is a measure that uses a diversity of data
analysis tools to deliver the decoration and relationships
in data sets that may be used to make authentic
predictions. The first step in data mining is to construe
the data .It instrument that summarize its statistical
attributes, visually critiqued it using charts and graphs,
and look for meaningful links amid variables .In the

Data Mining Process, collecting, analyze and selecting


the right data are alarmingly important one. To build a
auguring model based on patterns decisive from known
results, then verification that model build upon on results
outside the original pattern. A good model become never
be critical with existence. The final step is to analytically
verify the model. The main detached of the paper is to
maintain the affection of the data in data activity.
Various types of web services painting are used in
private advice transformation applications. These
freedom models are based on the assorted types of
Privacy Preserving Data boring (PPDM) techniques such
as Randomization method, unionization method and
inscription method. In many applications, certain PPDA
procedure agreement that nothing other than the final
analysis result is announce, it is impossible to check
even if participating parties are believable about their
private input data in data sharing. The incentive
adaptable privacy-preserving data analysis approach
have been developed that galvanize cooperate parties to
provide truthful inputs. The incentive adaptable privacy
preserving model has to combine with the users to
certify the action making use of the users ability. The EShopping is an application which provides a user
interaction admix that provides more security for
conscious (personal) information conversion compared
with the other aloofness preserving models. Aloofness
Preservation is most critical area in data mining. Privacy
Preservation approach are used to protect the users
private data from illegal person.
Data drilling includes various types of privacy
preservation approach:
1.
Data distribution
2.
Data modification
3.
Data mining algorithm
4.
Data or rule hiding
5.
Privacy preservation
Protected data sharing, various approaches are used to
composition the different privacy conserve models. The
Privacy-conserve data mining (PPDM), which mainly
considered four division of models such as Trust Third
Party Model , Semi-honest Model , malevolent Model
,Other Models-enticement Compatibility. The data
modification approach also includes four types of

www.ijsret.org

1126

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4, Issue 11, November 2015

approach such as Perturbation, which is consummate by


the alteration of an aspect value with a new value(i.e.,
changing a 1-value of a 0-value, or adding noise).
Blocking is the replacement of an actual aspect value
with an aggregation or merging which is the merger of
several values. Bargain that refers to interchanging
values of original evidence, and Sampling, which is
referred to bring the data for only a sample of a culture.
System Architecture
A improved data analysis model is generated which has
the capacity to compute the desired benign outcome of
data sharing for consider without having to actually
share or confess data. In many cases, battle parties who
have exclusive data may collaboratively conduct privacy
conserve distributed data analysis (PPDA) tasks to learn
benign data models or analysis results. For example,
contrasting credit card association may try to build better
models for credit card blackmail disclosure through
PPDA tasks. The figure 1 performs the model for
isolation Preserving System construction.
The system building of privacy defends gives the
detailed account about the function of the security
scheme in which it allows only the certified person. In
case, if any deceit user is trying to access the data bond
system will not allow user the access will be contradict
for the peculiar user . And the datas are retired from the
database bestow to the request given by user.

Fig 1: System Design


Impetus Marking
Consider what types of assigned functionalities could be
implemented in an impetus compatible fashion. In other
words, analyze which functionalities can be achieve in a
way that cooperate parties have the enticement to
provide their true private inputs upon alluring in the
corresponding SMC contract. The secure multiparty
computation course includes the following isolation
preserving data mining techniques:

Horizontal partitioning
For the table means to extract the fields that performing
extract the collection of incentive datas according to
particular customer. Perform this task to take the users
private detail as an input to the NCC model. Built the
DNCC model with help of Association rules technique
that provides information of this type in the form of ifthen statements.
Secure code computation process, is providing incentive
compatible secret code question for the NCC Model.
The computation process theorem consists of

following steps:
Step1: Select two fields from customer details from bank
database as input for secure code computation process.
Step2: Here first field is constant and another one field is
other information of customer details. For example (one
field is username that is constant, another one field is
other information like dob, accno, emailid, etc..).
Step3: Apply vertical partition on the first field data and
attaching second field in the middle of partition data
using Secure Sum Process technique.

2. RELATED WORK
In [1] paper, researcher defined to develop a credit card
fraud detection system using genetic algorithm. During
the credit card transaction, the fraud is detected and the
number of false alert is being minimized by using
genetic algorithm. Instead of maximizing the numbers of
correctly classified transactions we defined an objective
function where the misclassification costs are variable
and thus, correct classification of some transactions are
more important than correctly classifying the others. The
high amount of losses due to fraud and the awareness of
the relation between loss and the available limit have to
be reduced. The fraud has to be deducted in real time
and the number of false alert has to be minimized. There
are different devices helpful to do about that transaction.
The possible actions are blocking the card, sending SMS
or calling the card holder.
In [2] paper, researcher defined in financial institutions,
uses the fraud detection which is based on customer
behavior variables. The Sample data set has been
considered for the generating the fraud transactions and
detection of fraud in the electronic payment systems.
The various parameters are involved in the data set.
CCfreq= number of times card used CCloc = location at
which CCs in the hands of fraudsters CCoverdraft = the
rate of overdraft time CCbank balance = the balance
available at bank of CC CCdailyspending =the average
daily spending amount Data set T={t1,t2,t3,.,tn}, U is
one data object, If p parts of data set named S in data set
is far away from object U, S T, U T, then U is
Common object. The proposed system overcomes the

www.ijsret.org

1127

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4, Issue 11, November 2015

above mentioned issue in an efficient way. Using genetic


algorithm the fraud is detected and the false alert is
minimized and it produces an optimized result. The
fraud is detected based on the customers behavior. A
new classification problem which has a variable
misclassification cost is introduced. Here the genetic
algorithms is made where a set of interval valued
parameters are optimized.
In [3] paper, researcher defined Genetic algorithms are a
heuristic used to solve high-complexity computational
problems. Apart from modeling the phenomena
occurring in nature, they help in optimization,
simulation, modeling, design and prediction purposes in
science, medicine, technology, and everyday life [14]. A
recent survey of the state of the art was carried out for
the Materials and Manufacturing Processes journal in
2009, by Paszkowicz [14]. As the name of the journal
suggests they were only concerned with the application
of genetic algorithms to problems in chemistry and
physics, but nonetheless they highlighted some
innovative uses.
In [4] paper, researcher defined an example was to help
the design process of new materials, in particular with
regards to a reverse heat transfer problem. The problem
consists of finding a material with desirable thermal
properties that give rise to a good temperature field
profile. For a particular material well known equations
can be used to calculate the temperature profile, but
because of their complex nature the process cannot
easily be reversed to find optimal parameters. This is an
area where evolutionary search often excels, as we will
see in the next example where the search is applied to an
NP complete problem. The algorithm used in this case
modeled a liquid material that was being heated linearly
on its surface. The input to the algorithm, its initial
population, was properties of already known similar
liquids. The output computed for each liquid was the
temperature field and the cooling rate. Good results were
returned by the algorithm, which were later confirmed to
be correct experimentally.
In [5] paper, researcher defined still in the same
materials engineering survey, evolutionary search has
been applied to the mechanical process of welding. To
produce a strong weld several parameters have to be
optimized, such as current, voltage, torch speed, arc gap,
shielding gas and its flow rate, type and geometry of the
electrode. It can already be seen how this optimization
process could lend itself to the application of a genetic
algorithm, and once again good results were found for
what would have been an expensive experimental
process. Not only did the results of the optimization
provide a better set of welding parameters, they also
shed light on the transformation of the metal during the

weld. This had already been described theoretically, but


the results from the algorithm helped to bring
calculations and experimental results closer together. In
a purely theoretical area, genetic algorithms have been
applied to find approximate solutions to the travelling
salesman problem. Scaling became an issue as the
number of cities the salesman had to visit increased.
Braun [4] reported that the algorithm could generate
very good but not optimal solutions for travelling
salesman problems with 442 to 531 cities. Using a
standard SUN workstation they could optimally solve
problems with up to 442 cities in under thirty minutes.
In [6] paper, researcher defined the biggest problem
examined was 666 cities, which could be solved
approximately with a journey 0.04% longer than the
optimum route. Potvin also analyzed Travelling
Salesman with genetic algorithms [7]. The biggest
problem reported in his survey was one million cities,
solved to within 4% of an optimal route. This took four
hours on a powerful computer. He identified the role
played by the crossover operator on the outcome, with
performance being significantly affected by the
reordering of the tour. Perhaps the most well known
application of machine learning is robotic movement.
Schultz applied the algorithm so that autonomous robots
could navigate and perform collision avoidance of
obstacles in their path. An innovative part of his work
was once again aimed at cost and time saving, similar to
the previously detailed welding example. The task set
for the autonomous robot was to navigate from a start to
end point down no pre planned route, avoiding randomly
placed obstacles on its way.
EXISTING SYSTEM & DISADVANTAGES
In design incentive compatible privacy-preserving data
analysis techniques that motivate participating parties to
provide truthful input data. In this paper, we first
develop key theorems, then base on these theorem, we
analyze what types of privacy-preserving data analysis
tasks could be conducted in a way that telling the truth is
the best choice for any participating party.
Even though privacy-preserving data analysis techniques
guarantee that nothing other than the final result is
disclosed, whether or not participating parties provide
truthful input data cannot be verified. Although certain
PPDA techniques guarantee that nothing other than the
final analysis result is revealed, it is impossible to verify
whether or not participating parties are truthful about
their private input data. In other words, unless proper
incentives are set, even current PPDA techniques cannot
prevent participating parties from modifying their
private inputs.

www.ijsret.org

1128

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4, Issue 11, November 2015

3. PROPOSED SYSTEM
In this paper, A model has been proposed to design the
effective incentive compatible model for secure private
information transformation and identifying the fraud
transactions using Genetic Algorithm. Every user need
to transform the private data in many applications (EShopping) that must be protected from the hackers.
Building this model depends on many privacy
preserving data mining techniques like Cryptographic
techniques, Privacy preserving association rule and
Function Evaluation Theorem. The Incentive model is
very efficient for privacy preserving data mining,
because it provides the protocols against not only semihonest adversary model and also the malicious model
and we proposes identifies the fraud transactions based
on the users transactions knowledge.
Modules:

Privacy-Preserving Data Analysis.

Non-Cooperative Computation.

Analyzing Data Analysis Tasks In The


NCC Model.

Security System.
Privacy-Preserving Data Analysis:
The privacy preserving data analysis protocols
assume that participating parties are truthful about
their private input data. The techniques developed in
assume that each party has an internal device that can
verify whether they are telling the truth or not. In our
work, we do not assume the existence of such a device.
Instead, we try to make sure that providing the true input
is the best choice for a participating party.

tasks (without utilizing a TTP) that are incentive


compatible. We next prove several such important tasks
(as function with Boolean output, set operations, linear
functions, etc) that either satisfy or do not satisfy the
DNCC model. Also, note that the data analysis tasks
analyzed next have practical SMC implementations.
Security System:
The association rule mining and analyze whether
the association rule mining can be done in an incentive
compatible manner over horizontally and vertically
partitioned databases. The Security Code is valid means
perform the credit card operation otherwise not respond
the system.
Algorithm
Step 1: Initialize the population.
Step 2: Evaluate initial population.
Step 3: Repeat.
Step 4: Perform competitive selection.
Step 5: Apply genetic operators to generate new
Solutions.
Step 6: Evaluate solutions in the population
Until some convergence criteria is
Satisfied.

Non-Cooperative Computation:
(Get the security Code)
In the NCC model, each party
participates in a protocol to learn the output of some
given function f over the joint inputs of the parties.
First,
all
participating
parties send
their
private inputs securely to a trusted third party (TTP),
and then TTP computes f and sends back the result to
every participating party. The NCC model makes the
following assumptions.
1) Correctness:
The first priority for every participating party is to
learn the correct result;
2) Exclusiveness:
If possible, every participating party prefers to
learn the correct result exclusively.
Analyzing Data Analysis Tasks Ii the NCC Model:
Combining the two concepts DNCC and
SMC, we can analyze privacy preserving data analysis

Fig 2: Simple Method of Genetic Algorithm

4. REQUIREMENTS
Hardware: Single PC with (20 Gb Hard disc space 1Gb
RAM).
Software: Windows OS (xp, win 7), Net beans,
jdk1.8.0_60, My SQL, Tomcat.

www.ijsret.org

1129

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 4, Issue 11, November 2015

5. CONCLUSION
In this paper, we present to find the detection of credit
card fraud mechanism and examine the result based on
the principles of this algorithm. In this paper we saw
genetic algorithm that are being used to execute credit
card fraud how credit card fraud impact on financial
institution as well as merchant and customer, fraud
detection technique by genetic algorithm. The Genetic
algorithms are evolutionary algorithms in which the aim
is to obtain the better and optimal solutions. In this study
fraud detected and fraud transactions are generated with
the given sample data set. If this algorithm is applied
into bank credit card fraud detection system, the
probability of fraud transactions can be predicted soon
after credit card transactions by the banks. And a series
of anti-fraud strategies can be adopted to prevent banks
from great losses before and reduce risks.

REFERENCES
[1] S.Benson Edwin Raj, A. Annie Portia, Analysis on
Credit Card Fraud Detection Methods, IEEE
International Conference on Computer, Communication
and Electrical Technology, IEEE March 2011
[2] M.HamdiOzcelik, Mine Isik, Improving a credit
card fraud detection system using Genetic algorithm,
IEEE International Conference on Networking and
Information Technology, IEEE 2010.
[3] Genetic algorithms for credit card fraud detection by
Daniel Garner, IEEE Transactions May 2011.
[4] Research on credit card fraud detection model based
on distance sum IEEE 2009 International Joint
Conference on Artificial Intelligence.
[5] Credit card fraud detection using neural network,
RaghavedraPatidar, Lokesh Sharma, ISSN: 2231-2307,
Volume, IssueNCAI211,JUNE2011.
[6] Panigraili, S., Kundu, A., Sural, S. &Majumdar, A.
(2009). Credit Card Fraud Detection: A Fusion
Approach Using Dempster-Shafer Theory and Bayesian
Learning. Information Fusion , 354-363.
[7] Dr Markus Roggenbach. CS364 Software testing
slides. Swansea University, 2011.
[8]. D.WHITLEY, Genetic Algorithm and Neural
Network, 2003.
[9] Wang Xi. Some Ideas about Credit Card Fraud
Prediction China Trial. Apr. 2008, pp. 74-75.
[10] AmlanKundu, SuvasiniPanigrahi, ShamikSural and
Arun K. Majumdar, BLAST-SSAHA Hybridization
for Credit Card Fraud Detection, IEEE Transactions On
Dependable And Secure Computing, vol. 6, Issue no. 4,
pp.309-315, OctoberDecember 2009.
[11] AmlanKundu, SuvasiniPanigrahi, ShamikSural and
Arun K. Majumdar, Credit card fraud detection A
fusion approach using DempsterShafer theory and

Bayesian learning, Special Issue on Information Fusion


in Computer Security, Vol. 10, Issue no 4, pp.354- 363,
October 2009.
[12] Liu Ren, Zhang Liping, Zhan Yinqiang. A Study on
Construction of Analysis Based CRM System. Computer
Applications and Software. Vol.21, Apr. 2004, pp. 4647.
[13] A. Chiu, C. Tsai, A Web Services-Based
Collaborative Scheme for Credit Card Fraud Detection,
Proceedings of the IEEE International Conference on eTechnology, e-Commerce and e-Service, pp.177-181,
2004.
[14] M. Mehdi, S. Zair, A. Anou and M. Bensebti, A
Bayesian Networks in Intrusion Detection Systems,
International Journal of Computational Intelligence
Research, Issue No. 1, pp.0973- 1873 Vol. 3, 2007.
[15] Ezawa.K. &Norton.S,Constructing Bayesian
Networks to Predict Uncollectible Telecommunications
Accounts, IEEE Expert, October; 45-51, 1996.
[16] Blickle, T., & Thiele, L. (1995). A Comparison of
Selection Schemes used in Genetic Algorithms (Vol. 2).
Zurich: Swiss Federal Institute of Technology.
[17] JitendraDara,LaxmanGundemoni, Credit Card
Security and E-Payment. 2006.
[18] Wang Xi. Some Ideas about Credit Card Fraud
Prediction China Trial. Apr. 2008, pp. 74-75.
[19] M. HamdiOzcelik, EkremDuman, Mine Isik,
TugbaCevik, Improving a credit card fraud detection
system using genetic algorithm, International conference
on Networking and information technology 2010.
[20] Wen-Fang YU, Na Wang, Research on Credit Card
Fraud Detection Model Based on Distance Sum, IEEE
International Joint Conference on Artificial Intelligence
2009

www.ijsret.org

1130