SlideShare ist ein Scribd-Unternehmen logo
1 von 3
Downloaden Sie, um offline zu lesen
IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 10, 2015 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 1094
A Survey of Online Credit Card Fraud Detection using Data Mining
Techniques
Shruti J. Patel1 Palak V. Desai2
1
P.G. Student 2
Assistant Professor
1,2
Department of Computer Engineering
1,2
CGPIT, UkaTarsadiya University, Mahuva, Surat, Gujarat, India
Abstract—Nowadays the use of credit card has increased,
because the amount of online transaction is growing. With
the day to day use of credit card for payment online as well
as regular purchase, case of fraud associated with it is also
rising. To reduce the huge financial loss caused by frauds, a
number of modern techniques have been developed for
fraud detection which is based on data mining, neural
network, genetic algorithm etc. Here a survey of techniques
for online credit card fraud detection using Hidden Markov
Model, Genetic Algorithm and Hybrid Model, and
comparison between them has been shown.
Key words: Credit Card, Fraud Detection, Hidden Markov
Model, Genetic Algorithm, Hybrid Model Etc
I. INTRODUCTION
Credit card is a small plastic card which is issued to users as
system for payment [1]. It allows cardholders to purchase
goods and services based on the cardholder’s promise.
Nowadays the use of credit card has increased because of
the amount of online transaction is growing. Today, almost
every credit card carries an identifying number that helps in
shopping transaction fast. As credit card is used for payment
online as well as regular purchase, case of fraud associated
with it are also rising. Fraud is unauthorized activity made
for personal gain or to damage another user/individual [2].
Authorized user are permitted for credit card transactions by
using the parameters such as credit card number, signatures,
card holder’s address, expiry date etc. Illegal use of card or
card information without the knowledge of the cardholder
itself and thus is an act of criminal deception refers to credit
card fraud. There are two types of credit card fraud: offline
fraud and online fraud. Offline fraud is committed by using
a stolen physical card at call center or any place [7]. Online
fraud is committed via internet, phone, shopping, and web
or in absence of card holder. In online payment mode,
attacker need only little information like secure code, card
number, expiration date etc. for doing fraudulent transaction
[7]. Credit card fraud detection techniques are developed to
reduce the huge financial loss caused by frauds. Fraud
detection involves monitoring the behavior of users in order
to detect or avoid undesirable behavior. There are number of
techniques have been developed for fraud detection based
on data mining, neural network, genetic algorithm etc.
Fig. 1 shows the general scenario of credit card
fraud detection system. Here first step is to start and login
into a particular site to purchase goods and services. And
then go to the payment mode where credit card information
(credit card number, credit card cvv number, credit card
name, expiry date etc.) is necessary. Then personal identity
number (PIN) is asked for the verification. It also checks
whether the account balance of user’s credit card is more
than the purchase amount or not. After the verification fraud
detection system is activated. It concluded whether the
transaction is fraudulent or not. If it concluded that the
transaction is fraudulent then security question/answer
which was given at the time of registration is asked and if it
concluded that the transaction is not fraudulent then it is
direct given permission for transaction. At the end system is
terminated.
Fig. 1: Architecture of credit card fraud detection [7]
There are many data mining techniques for fraud
detection like hidden markov model, genetic algorithm,
hybrid model etc.
II. LITERATURE SURVEY
A. Hidden Markov Model:
Hidden markov model is the best techniques to detect online
credit card frauds. HMM is initially trained with the normal
behaviour of a cardholder [1]. It will be helpful to find out
the fraudulent transaction by using user’s spending profiles
which can be divided into major types: (1) Lower profile (2)
Middle profile (3) Higher profile. It stores the data of
different amount of transactions in form of clusters
depending on transaction amount which will be either in
low, medium or high value ranges and identify the spending
profile of cardholder. If the spending habit of the user is
determined to be having some different spending habits or
there is large amount of expenditure going on suddenly. So
an incoming credit card transaction is not accepted by the
trained Hidden Markov Model with sufficiently high
probability, it is considered to be fraudulent transactions.
The HMM uses the k-means algorithm for clustering
purpose and Baum welch algorithm for training purpose [1].
Hidden markov model reduces the work of
employee in bank since it maintains a log of transaction. It
produces high false alarm as well as high false positive [4].
A Survey of Online Credit Card Fraud Detection using Data Mining Techniques
(IJSRD/Vol. 3/Issue 10/2015/253)
All rights reserved by www.ijsrd.com 1095
Fig. 2 shows the working process of hidden markov
model for credit card fraud detection.
Fig. 2: Working process of hidden markov model [5]
B. Genetic Algorithm:
Genetic algorithms are evolutionary algorithms which aim at
obtaining better solutions. There are many parameters are
involved in dataset for credit card fraud detection.
CC freq = number of times card used
CC loc = location at which credit cards in the hands of
fraudsters
CC overdraft = the rate of overdraft time
CC bank balance = the balance available at bank of credit
card
CC daily spending =the average daily spending amount
The experimental process of genetic algorithm for
credit card fraud detection has four steps:
 Input group of data for credit card transactions. Get
the sample of data finally, which includes the
confidential information about the card holder,
store in the data set.
 Compute the critical values, Calculate the CC
usage frequency count, CC usage location, CC
overdraft, current bank balance, average daily
spending.
 Generate critical values found after limited number
of generations. Critical Fraud Detected using
Genetic algorithm.
1) Generate Fraud Transactions using this Algorithm.
Using genetic algorithm the fraud is detected and the false
alert is minimized and it gives a good performance [2].
C. Hybrid Model:
Hybrid model is a combination of hidden markov model,
behaviour based technique, genetic algorithm.
In hidden markov model, it works on spending
profile of cardholder which can be divided into lower
profile, medium profile and higher profile. The problem
with this approach is that it maintains log for previous
transaction. So many times false fraud are detected.
So in hybrid model, each and every transaction is
tested individually with this model which use hidden
markov model, behaviour based technique, genetic
algorithm. So by testing with all three method, values are
obtained in each case which is either in 0 or 1. Their average
value is taken out. If the average is greater than 0.4 then
fraud is detected [3].
III. COMPARATIVE ANALYSIS
I have compared techniques hidden markov model, genetic
algorithm and hybrid model with some parameter like true
positive (TP), false positive (FP), cost, accuracy etc.
A. True Positive (TP):
It represents the fraction of fraudulent transaction correctly
identified as fraudulent and genuine transactions correctly
identified as genuine [4].
B. False Positive (FP):
It represents fraction of genuine transactions identified as
fraudulent and fraudulent transactions identified as genuine
[4].
C. Accuracy:
It represents the fraction of total number of transaction (both
genuine and fraudulent) that has been detected correctly [4].
Parameter
Hidden
Markov
Model
Genetic
Algorithm
Hybrid
Model
Fraud
Detection
TP% Low [4] High [4] High [3]
FP% High [4] Low [4] Low [3]
Training
required
Yes [1] Yes [2] Yes [3]
Cost [4]
Quite
Expensive
Highly
Expensive
Highly
Expensive
Accuracy [4] Medium High Very High
Table 1: Comparison of various fraud detection method
Table 1. shows the comparison of various fraud
detection method. From Table 1, it is said that hybrid model
gives high true positive and low false positive than hidden
markov model and Genetic algorithm. All this techniques
has training required. Hybrid model is high expensive than
hidden markov model and genetic algorithm. But hybrid
model gives high accuracy than hidden markov model and
genetic algorithm.
IV. CONCLUSION
If one of these or combination of algorithm is applied into
bank credit card fraud detection system, the probability of
fraud transactions can be detected soon after credit card
transactions has been done. Genetic algorithm gives higher
accuracy than hidden markov model. Also genetic algorithm
gives high true positive (TP) and less false positive (FP)
than hidden markov model. If we use hybrid model than we
can get higher accuracy than hidden markov model and
genetic algorithm.
ACKNOWLEDGEMENT
I thanks to Ms. Palak Desai, Asst. prof., CE & IT Dept.,
CGPIT, Bardoli for their suggestion and for her
encouragement.
REFERENCES
[1] Iyer, Divya, Arti Mohanpurkar, Sneha Janardhan,
Dhanashree Rathod, and Amruta Sardeshmukh. "Credit
card fraud detection using Hidden Markov Model."
In Information and Communication Technologies
A Survey of Online Credit Card Fraud Detection using Data Mining Techniques
(IJSRD/Vol. 3/Issue 10/2015/253)
All rights reserved by www.ijsrd.com 1096
(WICT), 2011 World Congress on, pp. 1062-1066.
IEEE, 2011.
[2] RamaKalyani, K., and D. UmaDevi. "Fraud Detection
of Credit Card Payment System by Genetic
Algorithm." International Journal of Scientific &
Engineering Research 3, no. 7 (2012).
[3] Agrawal, Ayushi, Shiv Kumar, and Amit Kumar
Mishra. "A Novel Approach for Credit Card Fraud
Detection,” IEEE 2nd
International conference on
Computing for Sustainable Global Development, 2015.
[4] Raj, S. "Analysis on credit card fraud detection
methods." In Computer, Communication and Electrical
Technology (ICCCET), 2011 International Conference
on, pp. 152-156. IEEE, 2011.
[5] Srivastava, Abhinav, Amlan Kundu, Shamik Sural, and
Arun K. Majumdar. "Credit card fraud detection using
hidden Markov model." Dependable and Secure
Computing, IEEE Transactions on 5, no. 1 (2008): 37-
48.
[6] Bentley, Peter J., Jungwon Kim, Gil-Ho Jung, and
Jong-Uk Choi. "Fuzzy Darwinian Detection of Credit
Card Fraud." In the 14th Annual Fall Symposium of
the Korean Information Processing Society, 14th
October. 2000.
[7] Bhusari, V., and S. Patil. "Study of hidden markov
model in credit card fraudulent
detection." International Journal of Computer
Applications (0975–8887) Volume (2011).
[8] Gade, Vaibhav, and Sonal Chaudhari. "Credit Card
Fraud Detection Using Hidden Markov Model,”
International Journal of Emerging Technology and
Advanced Engineering, Vol. 2, Issue 7, July 2012.

Weitere ähnliche Inhalte

Was ist angesagt?

Credit card fraud detection
Credit card fraud detectionCredit card fraud detection
Credit card fraud detection
kalpesh1908
 

Was ist angesagt? (20)

Machine Learning for Fraud Detection
Machine Learning for Fraud DetectionMachine Learning for Fraud Detection
Machine Learning for Fraud Detection
 
Credit card fraud detection methods using Data-mining.pptx (2)
Credit card fraud detection methods using Data-mining.pptx (2)Credit card fraud detection methods using Data-mining.pptx (2)
Credit card fraud detection methods using Data-mining.pptx (2)
 
Credit card fraud detection pptx (1) (1)
Credit card fraud detection pptx (1) (1)Credit card fraud detection pptx (1) (1)
Credit card fraud detection pptx (1) (1)
 
Credit Card Fraud Detection
Credit Card Fraud DetectionCredit Card Fraud Detection
Credit Card Fraud Detection
 
A Study on Credit Card Fraud Detection using Machine Learning
A Study on Credit Card Fraud Detection using Machine LearningA Study on Credit Card Fraud Detection using Machine Learning
A Study on Credit Card Fraud Detection using Machine Learning
 
IRJET- Credit Card Fraud Detection using Random Forest
IRJET-  	  Credit Card Fraud Detection using Random ForestIRJET-  	  Credit Card Fraud Detection using Random Forest
IRJET- Credit Card Fraud Detection using Random Forest
 
Adaptive Machine Learning for Credit Card Fraud Detection
Adaptive Machine Learning for Credit Card Fraud DetectionAdaptive Machine Learning for Credit Card Fraud Detection
Adaptive Machine Learning for Credit Card Fraud Detection
 
Credit card fraud detection using machine learning Algorithms
Credit card fraud detection using machine learning AlgorithmsCredit card fraud detection using machine learning Algorithms
Credit card fraud detection using machine learning Algorithms
 
Credit card fraud detection
Credit card fraud detectionCredit card fraud detection
Credit card fraud detection
 
Detecting fraud with Python and machine learning
Detecting fraud with Python and machine learningDetecting fraud with Python and machine learning
Detecting fraud with Python and machine learning
 
credit card fraud detection
credit card fraud detectioncredit card fraud detection
credit card fraud detection
 
CREDIT CARD FRAUD DETECTION
CREDIT CARD FRAUD DETECTION CREDIT CARD FRAUD DETECTION
CREDIT CARD FRAUD DETECTION
 
Credit card fraud(1)
Credit card fraud(1)Credit card fraud(1)
Credit card fraud(1)
 
Credit card frauds
Credit card fraudsCredit card frauds
Credit card frauds
 
Uses of analytics in the field of Banking
Uses of analytics in the field of BankingUses of analytics in the field of Banking
Uses of analytics in the field of Banking
 
Short-Story-Writing 255.pptx
Short-Story-Writing 255.pptxShort-Story-Writing 255.pptx
Short-Story-Writing 255.pptx
 
Credit scorecard
Credit scorecardCredit scorecard
Credit scorecard
 
Healthcare fraud detection
Healthcare fraud detectionHealthcare fraud detection
Healthcare fraud detection
 
How To: Prevent Loan Application Fraud
How To: Prevent Loan Application FraudHow To: Prevent Loan Application Fraud
How To: Prevent Loan Application Fraud
 
Fraud Detection presentation
Fraud Detection presentationFraud Detection presentation
Fraud Detection presentation
 

Andere mochten auch

Guessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
Guessing CVV, Spoofing Payment and Experiences with Fraud Detection SystemsGuessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
Guessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
Positive Hack Days
 
65 113-121
65 113-12165 113-121
65 113-121
idescitation
 
Survey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease predictionSurvey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease prediction
Sivagowry Shathesh
 
Best topics for seminar
Best topics for seminarBest topics for seminar
Best topics for seminar
shilpi nagpal
 

Andere mochten auch (17)

Survey on Credit Card Fraud Detection Using Different Data Mining Techniques
Survey on Credit Card Fraud Detection Using Different Data Mining TechniquesSurvey on Credit Card Fraud Detection Using Different Data Mining Techniques
Survey on Credit Card Fraud Detection Using Different Data Mining Techniques
 
Fraud detection
Fraud detectionFraud detection
Fraud detection
 
Credit Card Fraud Detection Client Presentation
Credit Card Fraud Detection Client PresentationCredit Card Fraud Detection Client Presentation
Credit Card Fraud Detection Client Presentation
 
Presentation on fraud prevention, detection & control
Presentation on fraud prevention, detection & controlPresentation on fraud prevention, detection & control
Presentation on fraud prevention, detection & control
 
Guessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
Guessing CVV, Spoofing Payment and Experiences with Fraud Detection SystemsGuessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
Guessing CVV, Spoofing Payment and Experiences with Fraud Detection Systems
 
65 113-121
65 113-12165 113-121
65 113-121
 
Final ppt
Final pptFinal ppt
Final ppt
 
steganography using genetic algorithm along with visual cryptography for wire...
steganography using genetic algorithm along with visual cryptography for wire...steganography using genetic algorithm along with visual cryptography for wire...
steganography using genetic algorithm along with visual cryptography for wire...
 
Credit card fraud
Credit card fraudCredit card fraud
Credit card fraud
 
Steganography using visual cryptography
Steganography using visual cryptographySteganography using visual cryptography
Steganography using visual cryptography
 
Credit card fraud
Credit card fraudCredit card fraud
Credit card fraud
 
Survey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease predictionSurvey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease prediction
 
Credit Card Frauds
Credit Card FraudsCredit Card Frauds
Credit Card Frauds
 
Real-Time Fraud Detection in Payment Transactions
Real-Time Fraud Detection in Payment TransactionsReal-Time Fraud Detection in Payment Transactions
Real-Time Fraud Detection in Payment Transactions
 
Fraud principles1
Fraud principles1Fraud principles1
Fraud principles1
 
Fraud Detection Architecture
Fraud Detection ArchitectureFraud Detection Architecture
Fraud Detection Architecture
 
Best topics for seminar
Best topics for seminarBest topics for seminar
Best topics for seminar
 

Ähnlich wie A Survey of Online Credit Card Fraud Detection using Data Mining Techniques

credit card fraud analysis using predictive modeling python project abstract
credit card fraud analysis using predictive modeling python project abstractcredit card fraud analysis using predictive modeling python project abstract
credit card fraud analysis using predictive modeling python project abstract
Venkat Projects
 
credit card fruad detection from the fake users.pptx
credit card fruad detection from the fake users.pptxcredit card fruad detection from the fake users.pptx
credit card fruad detection from the fake users.pptx
227r1a0519
 

Ähnlich wie A Survey of Online Credit Card Fraud Detection using Data Mining Techniques (20)

IRJET- Survey on Credit Card Fraud Detection
IRJET- Survey on Credit Card Fraud DetectionIRJET- Survey on Credit Card Fraud Detection
IRJET- Survey on Credit Card Fraud Detection
 
An Identification and Detection of Fraudulence in Credit Card Fraud Transacti...
An Identification and Detection of Fraudulence in Credit Card Fraud Transacti...An Identification and Detection of Fraudulence in Credit Card Fraud Transacti...
An Identification and Detection of Fraudulence in Credit Card Fraud Transacti...
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER) International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Problem Reduction in Online Payment System Using Hybrid Model
Problem Reduction in Online Payment System Using Hybrid ModelProblem Reduction in Online Payment System Using Hybrid Model
Problem Reduction in Online Payment System Using Hybrid Model
 
IRJET - Online Credit Card Fraud Detection and Prevention System
IRJET - Online Credit Card Fraud Detection and Prevention SystemIRJET - Online Credit Card Fraud Detection and Prevention System
IRJET - Online Credit Card Fraud Detection and Prevention System
 
Tanvi_Sharma_Shruti_Garg_pre.pdf.pdf
Tanvi_Sharma_Shruti_Garg_pre.pdf.pdfTanvi_Sharma_Shruti_Garg_pre.pdf.pdf
Tanvi_Sharma_Shruti_Garg_pre.pdf.pdf
 
J017216164
J017216164J017216164
J017216164
 
Analysis of Spending Pattern on Credit Card Fraud Detection
Analysis of Spending Pattern on Credit Card Fraud DetectionAnalysis of Spending Pattern on Credit Card Fraud Detection
Analysis of Spending Pattern on Credit Card Fraud Detection
 
A Comparative Study on Online Transaction Fraud Detection by using Machine Le...
A Comparative Study on Online Transaction Fraud Detection by using Machine Le...A Comparative Study on Online Transaction Fraud Detection by using Machine Le...
A Comparative Study on Online Transaction Fraud Detection by using Machine Le...
 
FRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONSFRAUD DETECTION IN CREDIT CARD TRANSACTIONS
FRAUD DETECTION IN CREDIT CARD TRANSACTIONS
 
credit card fraud analysis using predictive modeling python project abstract
credit card fraud analysis using predictive modeling python project abstractcredit card fraud analysis using predictive modeling python project abstract
credit card fraud analysis using predictive modeling python project abstract
 
Online Transaction Fraud Detection using Hidden Markov Model & Behavior Analysis
Online Transaction Fraud Detection using Hidden Markov Model & Behavior AnalysisOnline Transaction Fraud Detection using Hidden Markov Model & Behavior Analysis
Online Transaction Fraud Detection using Hidden Markov Model & Behavior Analysis
 
IRJET - Fraud Detection in Credit Card using Machine Learning Techniques
IRJET -  	  Fraud Detection in Credit Card using Machine Learning TechniquesIRJET -  	  Fraud Detection in Credit Card using Machine Learning Techniques
IRJET - Fraud Detection in Credit Card using Machine Learning Techniques
 
Review on Fraud Detection in Electronic Payment Gateway
Review on Fraud Detection in Electronic Payment GatewayReview on Fraud Detection in Electronic Payment Gateway
Review on Fraud Detection in Electronic Payment Gateway
 
credit card fruad detection from the fake users.pptx
credit card fruad detection from the fake users.pptxcredit card fruad detection from the fake users.pptx
credit card fruad detection from the fake users.pptx
 
Credit Card Fraud Detection_ Mansi_Choudhary.pptx
Credit Card Fraud Detection_ Mansi_Choudhary.pptxCredit Card Fraud Detection_ Mansi_Choudhary.pptx
Credit Card Fraud Detection_ Mansi_Choudhary.pptx
 
IRJET- Finalize Attributes and using Specific Way to Find Fraudulent Transaction
IRJET- Finalize Attributes and using Specific Way to Find Fraudulent TransactionIRJET- Finalize Attributes and using Specific Way to Find Fraudulent Transaction
IRJET- Finalize Attributes and using Specific Way to Find Fraudulent Transaction
 
Vol 17 No 2 - July-December 2017
Vol 17 No 2 - July-December 2017Vol 17 No 2 - July-December 2017
Vol 17 No 2 - July-December 2017
 
Credit Card Fraud PPT - Reena Prajapati.pptx
Credit Card Fraud PPT - Reena Prajapati.pptxCredit Card Fraud PPT - Reena Prajapati.pptx
Credit Card Fraud PPT - Reena Prajapati.pptx
 
Credit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning AlgorithmCredit Card Fraud Detection System Using Machine Learning Algorithm
Credit Card Fraud Detection System Using Machine Learning Algorithm
 

Mehr von IJSRD

Mehr von IJSRD (20)

#IJSRD #Research Paper Publication
#IJSRD #Research Paper Publication#IJSRD #Research Paper Publication
#IJSRD #Research Paper Publication
 
Maintaining Data Confidentiality in Association Rule Mining in Distributed En...
Maintaining Data Confidentiality in Association Rule Mining in Distributed En...Maintaining Data Confidentiality in Association Rule Mining in Distributed En...
Maintaining Data Confidentiality in Association Rule Mining in Distributed En...
 
Performance and Emission characteristics of a Single Cylinder Four Stroke Die...
Performance and Emission characteristics of a Single Cylinder Four Stroke Die...Performance and Emission characteristics of a Single Cylinder Four Stroke Die...
Performance and Emission characteristics of a Single Cylinder Four Stroke Die...
 
Preclusion of High and Low Pressure In Boiler by Using LABVIEW
Preclusion of High and Low Pressure In Boiler by Using LABVIEWPreclusion of High and Low Pressure In Boiler by Using LABVIEW
Preclusion of High and Low Pressure In Boiler by Using LABVIEW
 
Prevention and Detection of Man in the Middle Attack on AODV Protocol
Prevention and Detection of Man in the Middle Attack on AODV ProtocolPrevention and Detection of Man in the Middle Attack on AODV Protocol
Prevention and Detection of Man in the Middle Attack on AODV Protocol
 
Comparative Analysis of PAPR Reduction Techniques in OFDM Using Precoding Tec...
Comparative Analysis of PAPR Reduction Techniques in OFDM Using Precoding Tec...Comparative Analysis of PAPR Reduction Techniques in OFDM Using Precoding Tec...
Comparative Analysis of PAPR Reduction Techniques in OFDM Using Precoding Tec...
 
Evaluation the Effect of Machining Parameters on MRR of Mild Steel
Evaluation the Effect of Machining Parameters on MRR of Mild SteelEvaluation the Effect of Machining Parameters on MRR of Mild Steel
Evaluation the Effect of Machining Parameters on MRR of Mild Steel
 
Filter unwanted messages from walls and blocking nonlegitimate user in osn
Filter unwanted messages from walls and blocking nonlegitimate user in osnFilter unwanted messages from walls and blocking nonlegitimate user in osn
Filter unwanted messages from walls and blocking nonlegitimate user in osn
 
Keystroke Dynamics Authentication with Project Management System
Keystroke Dynamics Authentication with Project Management SystemKeystroke Dynamics Authentication with Project Management System
Keystroke Dynamics Authentication with Project Management System
 
Diagnosing lungs cancer Using Neural Networks
Diagnosing lungs cancer Using Neural NetworksDiagnosing lungs cancer Using Neural Networks
Diagnosing lungs cancer Using Neural Networks
 
A Survey on Sentiment Analysis and Opinion Mining
A Survey on Sentiment Analysis and Opinion MiningA Survey on Sentiment Analysis and Opinion Mining
A Survey on Sentiment Analysis and Opinion Mining
 
A Defect Prediction Model for Software Product based on ANFIS
A Defect Prediction Model for Software Product based on ANFISA Defect Prediction Model for Software Product based on ANFIS
A Defect Prediction Model for Software Product based on ANFIS
 
Experimental Investigation of Granulated Blast Furnace Slag ond Quarry Dust a...
Experimental Investigation of Granulated Blast Furnace Slag ond Quarry Dust a...Experimental Investigation of Granulated Blast Furnace Slag ond Quarry Dust a...
Experimental Investigation of Granulated Blast Furnace Slag ond Quarry Dust a...
 
Product Quality Analysis based on online Reviews
Product Quality Analysis based on online ReviewsProduct Quality Analysis based on online Reviews
Product Quality Analysis based on online Reviews
 
Solving Fuzzy Matrix Games Defuzzificated by Trapezoidal Parabolic Fuzzy Numbers
Solving Fuzzy Matrix Games Defuzzificated by Trapezoidal Parabolic Fuzzy NumbersSolving Fuzzy Matrix Games Defuzzificated by Trapezoidal Parabolic Fuzzy Numbers
Solving Fuzzy Matrix Games Defuzzificated by Trapezoidal Parabolic Fuzzy Numbers
 
Study of Clustering of Data Base in Education Sector Using Data Mining
Study of Clustering of Data Base in Education Sector Using Data MiningStudy of Clustering of Data Base in Education Sector Using Data Mining
Study of Clustering of Data Base in Education Sector Using Data Mining
 
Fault Tolerance in Big Data Processing Using Heartbeat Messages and Data Repl...
Fault Tolerance in Big Data Processing Using Heartbeat Messages and Data Repl...Fault Tolerance in Big Data Processing Using Heartbeat Messages and Data Repl...
Fault Tolerance in Big Data Processing Using Heartbeat Messages and Data Repl...
 
Investigation of Effect of Process Parameters on Maximum Temperature during F...
Investigation of Effect of Process Parameters on Maximum Temperature during F...Investigation of Effect of Process Parameters on Maximum Temperature during F...
Investigation of Effect of Process Parameters on Maximum Temperature during F...
 
Review Paper on Computer Aided Design & Analysis of Rotor Shaft of a Rotavator
Review Paper on Computer Aided Design & Analysis of Rotor Shaft of a RotavatorReview Paper on Computer Aided Design & Analysis of Rotor Shaft of a Rotavator
Review Paper on Computer Aided Design & Analysis of Rotor Shaft of a Rotavator
 
A Survey on Data Mining Techniques for Crime Hotspots Prediction
A Survey on Data Mining Techniques for Crime Hotspots PredictionA Survey on Data Mining Techniques for Crime Hotspots Prediction
A Survey on Data Mining Techniques for Crime Hotspots Prediction
 

Kürzlich hochgeladen

An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
SanaAli374401
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
PECB
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 
Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.
MateoGardella
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
heathfieldcps1
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
QucHHunhnh
 

Kürzlich hochgeladen (20)

SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 

A Survey of Online Credit Card Fraud Detection using Data Mining Techniques

  • 1. IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 10, 2015 | ISSN (online): 2321-0613 All rights reserved by www.ijsrd.com 1094 A Survey of Online Credit Card Fraud Detection using Data Mining Techniques Shruti J. Patel1 Palak V. Desai2 1 P.G. Student 2 Assistant Professor 1,2 Department of Computer Engineering 1,2 CGPIT, UkaTarsadiya University, Mahuva, Surat, Gujarat, India Abstract—Nowadays the use of credit card has increased, because the amount of online transaction is growing. With the day to day use of credit card for payment online as well as regular purchase, case of fraud associated with it is also rising. To reduce the huge financial loss caused by frauds, a number of modern techniques have been developed for fraud detection which is based on data mining, neural network, genetic algorithm etc. Here a survey of techniques for online credit card fraud detection using Hidden Markov Model, Genetic Algorithm and Hybrid Model, and comparison between them has been shown. Key words: Credit Card, Fraud Detection, Hidden Markov Model, Genetic Algorithm, Hybrid Model Etc I. INTRODUCTION Credit card is a small plastic card which is issued to users as system for payment [1]. It allows cardholders to purchase goods and services based on the cardholder’s promise. Nowadays the use of credit card has increased because of the amount of online transaction is growing. Today, almost every credit card carries an identifying number that helps in shopping transaction fast. As credit card is used for payment online as well as regular purchase, case of fraud associated with it are also rising. Fraud is unauthorized activity made for personal gain or to damage another user/individual [2]. Authorized user are permitted for credit card transactions by using the parameters such as credit card number, signatures, card holder’s address, expiry date etc. Illegal use of card or card information without the knowledge of the cardholder itself and thus is an act of criminal deception refers to credit card fraud. There are two types of credit card fraud: offline fraud and online fraud. Offline fraud is committed by using a stolen physical card at call center or any place [7]. Online fraud is committed via internet, phone, shopping, and web or in absence of card holder. In online payment mode, attacker need only little information like secure code, card number, expiration date etc. for doing fraudulent transaction [7]. Credit card fraud detection techniques are developed to reduce the huge financial loss caused by frauds. Fraud detection involves monitoring the behavior of users in order to detect or avoid undesirable behavior. There are number of techniques have been developed for fraud detection based on data mining, neural network, genetic algorithm etc. Fig. 1 shows the general scenario of credit card fraud detection system. Here first step is to start and login into a particular site to purchase goods and services. And then go to the payment mode where credit card information (credit card number, credit card cvv number, credit card name, expiry date etc.) is necessary. Then personal identity number (PIN) is asked for the verification. It also checks whether the account balance of user’s credit card is more than the purchase amount or not. After the verification fraud detection system is activated. It concluded whether the transaction is fraudulent or not. If it concluded that the transaction is fraudulent then security question/answer which was given at the time of registration is asked and if it concluded that the transaction is not fraudulent then it is direct given permission for transaction. At the end system is terminated. Fig. 1: Architecture of credit card fraud detection [7] There are many data mining techniques for fraud detection like hidden markov model, genetic algorithm, hybrid model etc. II. LITERATURE SURVEY A. Hidden Markov Model: Hidden markov model is the best techniques to detect online credit card frauds. HMM is initially trained with the normal behaviour of a cardholder [1]. It will be helpful to find out the fraudulent transaction by using user’s spending profiles which can be divided into major types: (1) Lower profile (2) Middle profile (3) Higher profile. It stores the data of different amount of transactions in form of clusters depending on transaction amount which will be either in low, medium or high value ranges and identify the spending profile of cardholder. If the spending habit of the user is determined to be having some different spending habits or there is large amount of expenditure going on suddenly. So an incoming credit card transaction is not accepted by the trained Hidden Markov Model with sufficiently high probability, it is considered to be fraudulent transactions. The HMM uses the k-means algorithm for clustering purpose and Baum welch algorithm for training purpose [1]. Hidden markov model reduces the work of employee in bank since it maintains a log of transaction. It produces high false alarm as well as high false positive [4].
  • 2. A Survey of Online Credit Card Fraud Detection using Data Mining Techniques (IJSRD/Vol. 3/Issue 10/2015/253) All rights reserved by www.ijsrd.com 1095 Fig. 2 shows the working process of hidden markov model for credit card fraud detection. Fig. 2: Working process of hidden markov model [5] B. Genetic Algorithm: Genetic algorithms are evolutionary algorithms which aim at obtaining better solutions. There are many parameters are involved in dataset for credit card fraud detection. CC freq = number of times card used CC loc = location at which credit cards in the hands of fraudsters CC overdraft = the rate of overdraft time CC bank balance = the balance available at bank of credit card CC daily spending =the average daily spending amount The experimental process of genetic algorithm for credit card fraud detection has four steps:  Input group of data for credit card transactions. Get the sample of data finally, which includes the confidential information about the card holder, store in the data set.  Compute the critical values, Calculate the CC usage frequency count, CC usage location, CC overdraft, current bank balance, average daily spending.  Generate critical values found after limited number of generations. Critical Fraud Detected using Genetic algorithm. 1) Generate Fraud Transactions using this Algorithm. Using genetic algorithm the fraud is detected and the false alert is minimized and it gives a good performance [2]. C. Hybrid Model: Hybrid model is a combination of hidden markov model, behaviour based technique, genetic algorithm. In hidden markov model, it works on spending profile of cardholder which can be divided into lower profile, medium profile and higher profile. The problem with this approach is that it maintains log for previous transaction. So many times false fraud are detected. So in hybrid model, each and every transaction is tested individually with this model which use hidden markov model, behaviour based technique, genetic algorithm. So by testing with all three method, values are obtained in each case which is either in 0 or 1. Their average value is taken out. If the average is greater than 0.4 then fraud is detected [3]. III. COMPARATIVE ANALYSIS I have compared techniques hidden markov model, genetic algorithm and hybrid model with some parameter like true positive (TP), false positive (FP), cost, accuracy etc. A. True Positive (TP): It represents the fraction of fraudulent transaction correctly identified as fraudulent and genuine transactions correctly identified as genuine [4]. B. False Positive (FP): It represents fraction of genuine transactions identified as fraudulent and fraudulent transactions identified as genuine [4]. C. Accuracy: It represents the fraction of total number of transaction (both genuine and fraudulent) that has been detected correctly [4]. Parameter Hidden Markov Model Genetic Algorithm Hybrid Model Fraud Detection TP% Low [4] High [4] High [3] FP% High [4] Low [4] Low [3] Training required Yes [1] Yes [2] Yes [3] Cost [4] Quite Expensive Highly Expensive Highly Expensive Accuracy [4] Medium High Very High Table 1: Comparison of various fraud detection method Table 1. shows the comparison of various fraud detection method. From Table 1, it is said that hybrid model gives high true positive and low false positive than hidden markov model and Genetic algorithm. All this techniques has training required. Hybrid model is high expensive than hidden markov model and genetic algorithm. But hybrid model gives high accuracy than hidden markov model and genetic algorithm. IV. CONCLUSION If one of these or combination of algorithm is applied into bank credit card fraud detection system, the probability of fraud transactions can be detected soon after credit card transactions has been done. Genetic algorithm gives higher accuracy than hidden markov model. Also genetic algorithm gives high true positive (TP) and less false positive (FP) than hidden markov model. If we use hybrid model than we can get higher accuracy than hidden markov model and genetic algorithm. ACKNOWLEDGEMENT I thanks to Ms. Palak Desai, Asst. prof., CE & IT Dept., CGPIT, Bardoli for their suggestion and for her encouragement. REFERENCES [1] Iyer, Divya, Arti Mohanpurkar, Sneha Janardhan, Dhanashree Rathod, and Amruta Sardeshmukh. "Credit card fraud detection using Hidden Markov Model." In Information and Communication Technologies
  • 3. A Survey of Online Credit Card Fraud Detection using Data Mining Techniques (IJSRD/Vol. 3/Issue 10/2015/253) All rights reserved by www.ijsrd.com 1096 (WICT), 2011 World Congress on, pp. 1062-1066. IEEE, 2011. [2] RamaKalyani, K., and D. UmaDevi. "Fraud Detection of Credit Card Payment System by Genetic Algorithm." International Journal of Scientific & Engineering Research 3, no. 7 (2012). [3] Agrawal, Ayushi, Shiv Kumar, and Amit Kumar Mishra. "A Novel Approach for Credit Card Fraud Detection,” IEEE 2nd International conference on Computing for Sustainable Global Development, 2015. [4] Raj, S. "Analysis on credit card fraud detection methods." In Computer, Communication and Electrical Technology (ICCCET), 2011 International Conference on, pp. 152-156. IEEE, 2011. [5] Srivastava, Abhinav, Amlan Kundu, Shamik Sural, and Arun K. Majumdar. "Credit card fraud detection using hidden Markov model." Dependable and Secure Computing, IEEE Transactions on 5, no. 1 (2008): 37- 48. [6] Bentley, Peter J., Jungwon Kim, Gil-Ho Jung, and Jong-Uk Choi. "Fuzzy Darwinian Detection of Credit Card Fraud." In the 14th Annual Fall Symposium of the Korean Information Processing Society, 14th October. 2000. [7] Bhusari, V., and S. Patil. "Study of hidden markov model in credit card fraudulent detection." International Journal of Computer Applications (0975–8887) Volume (2011). [8] Gade, Vaibhav, and Sonal Chaudhari. "Credit Card Fraud Detection Using Hidden Markov Model,” International Journal of Emerging Technology and Advanced Engineering, Vol. 2, Issue 7, July 2012.