SITE

January,2018

ANALYSIS ON CREDIT CARD FRAUD

DETECTION METHODS

Submitted in partial fulfillment for the award of the degree of

MASTER OF COMPUTER APPLICATIONS

by

PRAKHAR DHAMIJA(16MCA0073)
 ABSTRACT

E-Commerce is the most beneficial solution to expand the customer base and achieve the largest
platform with a very small investment. The rapid growth in the E-Commerce has dramatically
increased credit cards usage for online purchases and it induced blowup in the credit card fraud.
For both online as well as regular purchase credit card became the most popular mode of
payment, fraud cases connected with it are also arising. The fraudulent transactions are confused
with genuine transactions and the simple pattern matching techniques are not often enough to
detect those frauds accurately. Efficient fraud detection system implementation became
imperative for all credit card issuing banks to minimize their losses. Modern techniques based on
Artificial Intelligence, Data mining, Fuzzy logic, Machine learning, Sequence Alignment,
Genetic Programming etc., are evolved in detecting various credit card fraudulent transactions.
These approaches certainly lead to an efficient credit card fraud detection system. This project
presents a survey of various techniques used in credit card fraud detection mechanisms and
evaluates each methodology based on certain design criteria.
 INTRODUCTION

Credit card fraud can be defined as “Unauthorized account activity by a person for which the
account was not intended. Operationally, this is an event for which action can be taken to stop
the abuse in progress and incorporate risk management practices to protect against similar
actions in the future”. In simple terms, Credit Card Fraud is defined as when an individual uses
another individual’s credit card for personal reasons while the owner of the card and the card
issuer are not aware of the fact that the card is being used. And the persons using the card has not
at all having the connection with the cardholder or the issuer and has no intention of making the
repayments for the purchase they done. Fraud detection involves identifying Fraud as quickly as
possible once it has been perpetrated. Fraud detection methods are continuously developed to
defend criminals in adapting to their strategies. The development of new fraud detection methods
is made more difficult due to the severe limitation of the exchange of ideas in fraud detection.
Data sets are not made available and results are often not disclosed to the public. The fraud cases
have to be detected from the available huge data sets such as the logged data and user behavior.
At present, fraud detection has been implemented by a number of methods such as data mining,
statistics, and artificial intelligence. Fraud is discovered from anomalies in data and patterns. The
different types of methods for committing credit card frauds are described below.
 LITERATURE SURVEY

Title: BLAST-SSAHA Hybridization for Credit Card Fraud Detection

Author: Amlan Kundu, Suvasini Panigrahi, Shamik Sural and Arun K. Majumdar
Description:

A phenomenal growth in the number of credit card transactions, especially for online purchases,
has recently led to a substantial rise in fraudulent activities. Implementation of efficient fraud
detection systems has thus become imperative for all credit card issuing banks to minimize their
losses. In real life, fraudulent transactions are interspersed with genuine transactions and simple
pattern matching is not often sufficient to detect them accurately. Thus, there is a need for
combining both anomaly detection as well as misuse detection techniques. In this paper, we
propose to use two-stage sequence alignment in which a profile analyzer (PA) first determines
the similarity of an incoming sequence of transactions on a given credit card with the genuine
cardholder's past spending sequences. The unusual transactions traced by the profile analyzer are
next passed on to a deviation analyzer (DA) for possible alignment with past fraudulent
behavior. The final decision about the nature of a transaction is taken on the basis of the
observations by these two analyzers. In order to achieve online response time for both PA and
DA, we suggest a new approach for combining two sequence alignment algorithms BLAST and
SSAHA
TITLE: Fast algorithms for mining association rules in large databases
AUTHOR: R. AGRAWAL AND R. SRIKANT.
DESCRIPTION:

The major consequences are loss of billions of dollars each year, investor confidence or
corporate reputation. A study area called Financial Fraud Detection (FFD) is obligatory, in order
to prevent the destructive results caused by financial fraud. In this study, we propose a new
method based on Grammar-based Genetic Programming (GBGP), multi-objectives optimization
and ensemble learning for solving FFD problems. We comprehensively compare the proposed
method with Logistic Regression (LR), Neural Networks (NNs), Support Vector Machine
(SVM), Bayesian Networks (BNs), Decision Trees (DTs), AdaBoost, Bagging and LogitBoost
on four FFD datasets. The experimental results showed the effectiveness of the new approach in
the given FFD problems including two real-life problems. The major implications and
significances of the study can concretely generalize for two points. First, it evaluates a number of
data mining techniques by the given real-life classification problems. Second, it suggests a new
method based on GBGP, NSGA-II and ensemble learning.
TITLE: Why we tag: Motivations for annotation in mobile and online media
AUTHOR: M. AMES AND M. NAAMAN.
DESCRIPTION:

Financial fraud is a criminal act, which violates the law, rules or policy to gain unauthorized
financial benefit. The major consequences are loss of billions of dollars each year, investor
confidence or corporate reputation. A study area called Financial Fraud Detection (FFD) is
obligatory, in order to prevent the destructive results caused by financial fraud. In this study, we
propose a new method based on Grammar-based Genetic Programming (GBGP), multi-
objectives optimization and ensemble learning for solving FFD problems. We comprehensively
compare the proposed method with Logistic Regression (LR), Neural Networks (NNs), Support
Vector Machine (SVM), Bayesian Networks (BNs), Decision Trees (DTs), AdaBoost, Bagging
and LogitBoost on four FFD datasets. The experimental results showed the effectiveness of the
new approach in the given FFD problems including two real-life problems. The major
implications and significances of the study can concretely generalize for two points. First, it
evaluates a number of data mining techniques by the given real-life classification problems.
Second, it suggests a new method based on GBGP, NSGA-II and ensemble learning.
TITLE: Fuzzy Darwinian detection of credit card fraud
AUTHOR: PETER J. BENTLEY, JUNGWON KIM, GIL-HO JUNG AND
JONG-UK CHOI
DESCRIPTION:

By the exponential growth of Credit Card user the fraudulent transactions also have increased
dramatically. The genuine transaction and fraudulent transactions are almost similar, so it is very
hard to discover a fraudulent transaction form the genuine one. In this paper we have proposed
fraud detection algorithm based on Fuzzy-ID3. Intermediate nodes we split using attribute
having highest information gain. The leaf nodes classifies the transactions as fraud, doubtful or
normal. Experimental result exhibits that the technique is efficient one in detecting frauds.
Title: Credit card fraud detection using Big data
Author: Sam Maes, Karl Tuyls, Bram Vanschoenwinkel, Bernard Manderick,
Description:

Big data is the frontier of a firm’s ability to store, process and access all the data and it needs to
operate effectively for decision making, reduce risks and serve customer. The 3 main
characterstic of big data volume (data quantity), velocity (data speed), variety (data type), Big
data can handle more than 1 million customer transaction per hour. Hadoop is an apache top
level project, open source implementation of frameworks for reliable, scalable, distributed
computing and data storage. It is a flexible and highly-available architecture for large scale
computation and data processing on a network of commodity hardware. Big data helps financial
institutions to approach fraud in different ways and possibly get different results. For the credit
card fraud detection we need bank, transaction and customer data.
 SURVEY TABLE

SOURCE SAMPLE/STUDY PURPOSE RESULTS

DESCRIPTION
BLAST-SSAHA A phenomenal growth The transactions and In order to achieve
Hybridization for in the number of simple pattern online response time
credit card matching is not often for both PA and DA,
Credit Card Fraud
transactions, sufficient to detect we suggest a new
Detection especially for online them accurately. approach for
purchases, has Thus, there is a need combining two
recently led to a for combining both sequence alignment
Author: Amlan
substantial rise in anomaly detection as algorithms BLAST
Kundu, Suvasini fraudulent activities. well as misuse and SSAHA
Panigrahi, Shamik Implementation of detection techniques
efficient fraud
Sural and Arun K.
detection systems has
Majumdar thus become
imperative for all
credit card issuing
banks to minimize
their losses
Title: Fast algorithms Financial fraud is a , in order to prevent First, it evaluates a
for mining association criminal act, which the destructive results number of data
violates the law, rules caused by financial
rules in large mining techniques by
or policy to gain fraud. In this study,
databases. unauthorized financial we propose a new the given real-life
benefit. The major method based on classification
consequences are loss Grammar-based
Author: R. Agrawal problems. Second, it
of billions of dollars Genetic Programming
and R. Srikant. each year, investor (GBGP), multi- suggests a new
. confidence or objectives method based on
corporate reputation optimization and
GBGP, NSGA-II and
ensemble learning for
solving FFD problems ensemble learning.
Title: Why we tag:
Motivations for Financial fraud is a The comprehensively The major
criminal act, which compare the proposed implications and
annotation in mobile
violates the law, rules method with Logistic significances of the
and online media. or policy to gain Regression (LR), study can concretely
unauthorized financial Neural Networks generalize for two
benefit. The major (NNs), Support points. First, it
Author: M. Ames and
consequences are loss Vector Machine evaluates a number of
M. Naaman. of billions of dollars (SVM), Bayesian data mining
each year, investor Networks (BNs), techniques by the
confidence or Decision Trees (DTs), given real-life
corporate reputation. AdaBoost, Bagging classification
and LogitBoost on problems. Second, it
four FFD datasets. suggests a new
method based on
GBGP, NSGA-II and
ensemble
Title: “Fuzzy The exponential The genuine In this paper we have
Darwinian Detection growth of Credit Card transaction and proposed fraud
user the fraudulent fraudulent detection algorithm
of Credit Card Fraud
transactions also have transactions are based on Fuzzy-ID3.
Author: Peter J. increased dramatically almost similar, so it is Intermediate nodes
Bentley, Jungwon very hard to discover we split using
a fraudulent attribute having
Kim, Gil-Ho Jung and
transaction highest information
Jong-Uk Choi gain.
SOURCE SAMPLE/STUDY PURPOSE RESULTS
DESCRIPTION
Title: Credit card Financial The major evaluates a number of
fraud detection using fraud is a criminal act, consequences are loss data mining
which violates the of billions of dollars techniques by the
Bayesian and neural
law, rules or policy to each year, investor given real-life
networks, gain unauthorized confidence or classification
Author: Sam Maes, financial benefit. corporate reputation. problems. Second, it
A study area called suggests a new
Karl Tuyls, Bram
Financial Fraud method based on
Vanschoenwinkel, Detection (FFD) is GBGP, NSGA-II and
Bernard Manderick obligatory ensemble learning.

EXISTING SYSTEM:

Most of the time, the genuine cardholder is not aware that someone else has seen or stolen his
card information. The only way to detect this kind of fraud is to analyze the spending patterns on
every card and to figure out any inconsistency with respect to the “usual” spending patterns.
Fraud detection based on the analysis of existing purchase data of cardholder is a promising way
to reduce the rate of successful credit card frauds. Since humans tend to exhibit specific
behaviorist profiles, every cardholder can be represented by a set of patterns containing
information about the typical purchase category, the time since the last purchase, the amount of
money spent, etc. Deviation from such patterns is a potential threat to the system.

DISADVANTAGES:
• The main disadvantage of the existing system is the detection occurs only after gets a
written complaint.
• In the existing system there is physical inconvenience exists.
• The period occurs to detect the fraud will cause so many losses to the cardholder.
 • There is no particular security system in the existing so a hacker can easily access others
card.

PROPOSED SYSTEM:

Credit card fraudulent detection which is done using HMM (Hidden Markov Model). This
technique is used to detect various suspicious activities on credit card. It maintains a database,
where past records of transactions are saved and any unusual transaction if carried out, which
differs too much from the previous records, it tracks it. Let the user know by sending the details
of the transaction on his mobile and hence prevent fraud . The particulars of purchased items in
single transactions are generally unknown to any Credit card Fraud Detection System running
either at the bank that issues credit cards to the cardholders or at the merchant site where goods is
going to be purchased. [1] The implementation techniques of Hidden Markov Model in order to
detect fraud transaction through credit cards, it create clusters of training set and identify the
spending profile of cardholder.
ADVANTAGES:
Most of the time, the genuine cardholder is not aware that someone else has
seen or stolen his card information. The only way to detect this kind of fraud is to analyze the
spending patterns on every card and to figure out any inconsistency with respect to the “usual”
spending patterns. Fraud detection based on the analysis of existing purchase data of
cardholder is a promising way to reduce the rate of successful credit card frauds. Since humans
tend to exhibit specific behaviorist profiles, every cardholder can be represented by a set of
patterns containing information about the typical purchase category, the time since the last
purchase, the amount of money spent, etc. Deviation from such patterns is a potential threat to
the system.

SYSTEM ARCHITECTURE

DATA
WAREHOUSE
(CUSTOMER
DATA)

FRAUD RULE RULES FILTER &

SET ENGINE PRIORITY

GENETIC
ALGORITHM
SEQUENCE DIAGRAM:
ACTIVITY DIAGRAM:
USE CASE:
UML DIAGRAM:
 REFERENCES

[1] Amlan Kundu, Suvasini Panigrahi, Shamik Sural 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, October-December 2009.
[2] Amlan Kundu, Suvasini Panigrahi, Shamik Sural and Arun K. Majumdar, “Credit card fraud
detection: A fusion approach using Dempster–Shafer theory and Bayesian learning,” Special
Issue on Information Fusion in Computer Security, Vol. 10, Issue no 4, pp.354- 363, October
2009.
[3] Abhinav Srivastava, Amlan Kundu, Shamik Sural, Arun K. Majumdar, “Credit Card Fraud
Detection using Hidden Markov Model,” IEEE Transactions On Dependable And Secure
Computing, vol. 5, Issue no. 1, pp.37-48, January-March 2008.
[4] Peter J. Bentley, 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.
[5] Sam Maes, Karl Tuyls, Bram Vanschoenwinkel, Bernard Manderick, “Credit card fraud
detection using Bayesian and neural networks,” Interactive image-guided neurosurgery, pp.261-
270, 1993.
[6] Amlan Kundu, S. Sural, A.K. Majumdar, “Two-Stage Credit Card Fraud Detection Using
Sequence Alignment,” Lecture Notes in Computer Science, Springer Verlag, Proceedings of the
International Conference on Information Systems Security, Vol. 4332/2006, pp.260- 275, 2006.
[7] Simon Haykin, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, pp.842,
1999.