proj report
TRANSCRIPT
Credit Card Fraud Detection System
Chapter 1
Problem Definition
Department of Computer Engineering,Tathwade 1
Credit Card Fraud Detection System
1.1 Problem Definition
Design the software to implement computerized credit card fraud detection
system. It mainly consists of customer, credit card, system, administrator, message
sending system as mobile phones and computer.
There are two phases of system, one is online credit card transaction and the other
is credit card machine terminal transaction. The system must try to detect any kind of
fraud, for instance change of place, excessive amount, abnormal timing or behavior and
even the unusual frequency of transaction.
The system will develop an entity set using bank database. A credit card
transaction simulator is used to generate transactions randomly; these transactions are fed
to the system as an input. System will also have its own memory and will use A.I.
techniques and methodologies to prevent any misuse of the credit card.
Incase of any fraud the system will send an email or SMS whichever is feasible to
the owner of the credit card this will be considered as an output of the system.
An entity set is generated considering previous history of the customer stored in
the bank database; this is termed as profile of the customer. The profile of customer is
maintained by the bank and is assumed to be updated by the system regularly. The profile
of the customer will be generated by the system considering previous transactions of the
customer if present. The system will generate output to fraudulent transactions so as it
does not cause nuisance to the customer, for example if a customer is alerted for a
fraudulent transaction and the customer approves the transaction as non fraudulent, then
next time similar transaction will not generate fraud message. The entity set contains
variables which are having priorities associated with each of them. These will focus on
chances of detecting a transaction as a fraudulent transaction.
Department of Computer Engineering,Tathwade 2
Credit Card Fraud Detection System
System administrator will assign priorities to each transaction parameter considering
customer requirements. E.g. User will give list of possible favorites such as grocery,
petrol, electronic goods etc.
AI technique in the system will see to it that the system does consider previously
detected fraudulent transactions which were approved by the customer to be non-
fraudulent.
1.2 Aim
1.3 Literature Servey:
Recent Developments in Fraud Management
The technology for detecting credit card frauds is advancing at a rapid pace –
rules based
Systems, neural networks, chip cards and biometrics are some of the popular
techniques Employed by Issuing and Acquiring banks these days. Apart from
technological advances, another trend which has emerged during the recent years is that
fraud prevention is moving from back-office transaction processing systems to front-
office authorization systems to prevent committing of potentially fraudulent transactions.
However, this is a challenging trade-off between the response time for processing an
authorization request and extent of screening that should be carried out.
SIMPLE RULE SYSTEMS:
Simple rule systems involve the creation of ‘if...then’ criteria to filter incoming
Authorizations/transactions. Rule-based systems rely on a set of expert rules designed to
Department of Computer Engineering,Tathwade 3
Credit Card Fraud Detection System
identify specific types of high-risk transactions. Rules are created using the knowledge of
what characterizes fraudulent transactions. For instance, a rule could look like – If
transaction amount is > $5000 and card acceptance location = Casino and Country = ‘a
high-risk country’. Fraud rules enable to automate the screening processes leveraging the
knowledge gained over time regarding the characteristics of both fraudulent and
legitimate transactions. Typically, the effectiveness of a rule-based system will increase
over time, as more rules are added to the system. It should be clear, however, that
ultimately the effectiveness of the system depends on the knowledge and expertise of the
person designing the rules.
The disadvantage of this solution is that it can increase the probability of throwing
many Valid transactions as exceptions, however, there are ways by which this limitation
can be overcome to some extent by prioritizing the rules and fixing limits on number of
filtered Transactions.
RISK SCORING TECHNOLOGIES
Risk scoring tools are based on statistical models designed to recognize fraudulent
transactions, based on a number of indicators derived from the transaction characteristics.
Typically, these tools generate a numeric score indicating the likelihood of a transaction
being fraudulent: the higher the score, the more suspicious the order. Risk scoring
systems provide one of the most effective fraud prevention tools available.
The primary advantage of risk scoring is the comprehensive evaluation of a
transaction being captured by a single number. While individual fraud rules typically
evaluate a few simultaneous conditions, a risk-scoring system arrives at the final score by
weighting several dozens of fraud indicators, derived from the current transaction
attributes as well as cardholder historical activities. E.g., transaction amounts more that
three times the average transaction amount for the cardholder in the last one year.
The second advantage of risk scoring is that, while a fraud rule would either flag
or not flag a transaction, the actual score indicates the degree of suspicion on each
Department of Computer Engineering,Tathwade 4
Credit Card Fraud Detection System
transaction.Thus, transactions can be prioritized based on the risk score and given a
limited capacity for manual review, only those with the highest score would be reviewed.
NEURAL NETWORK TECHNOLOGIES
Neural networks are an extension of risk scoring techniques. They are based on
the‘statistical knowledge’ contained in extensive databases of historical transactions, and
fraudulent ones in particular. These neural network models are basically ‘trained’ by
using examples of both legitimate and fraudulent transactions and are able to correlate
and weigh various fraud indicators (e.g., unusual transaction amount, card history, etc)
to the occurrence of fraud. A neural network is a computerized system that sorts data
logically by performing the following tasks:
1. Identifies cardholder’s buying and fraudulent activity patterns.
2. Processes data by trial and elimination (excluding data that is not relevant to the
pattern).
3. Finds relationships in the patterns and current transaction data.
The principles of neural networking are motivated by the functions of the brain –
especially pattern recognition and associative memory. The neural network recognizes
similar patterns, predicting future values or events based upon the associative memory of
the patterns it has learned. The advantages neural networks offer over other techniques
are that these models are able to learn from the past and thus, improve results as time
passes. They can also extract rules and predict future activity based on the current
situation. By employing neural networks effectively, banks can detect fraudulent use of a
card, faster and more efficiently.
BIOMETRICS
Biometrics is the name given to a fraud prevention technique that records a unique
characteristic of the cardholder like, a fingerprint or how he/she sign his/her name, so
Department of Computer Engineering,Tathwade 5
Credit Card Fraud Detection System
Understanding Credit Card Frauds that it can be read by a computer. The computer can
then compare the stored characteristic with that of the person presenting the card to make
sure that the right person has the right card. Biometrics, which provides a means to
identify an individual through the verification of unique physical or behavioral
characteristics, seems to supercede PIN as a basis for the next generation of personal
identity verification systems.
There are many types of biometrics systems under development such as finger print
verification, hand based verification, retinal and iris scanning and dynamic signature
verification.
SMART CARDS
To define in the simplest terms, a smart card is a credit card with some intelligence in the
form of an embedded CPU. This card-computer can be programmed to perform tasks and
store information, but the intelligence is limited – meaning that the smart card's power
falls far short of a desktop computer.
Smart credit cards operate in the same way as their magnetic counterparts, the only
difference being that an electronic chip is embedded in the card. These smart chips add
extra security to the card. Smart credit cards contain 32-kilobyte microprocessors, which
is capable of generating 72 quadrillion or more possible encryption keys and thus making
it practically impossible to fraudulently decode information in the chip.
The smart chip has made credit cards a lot more secure; however, the technology is still
being run alongside the magnetic strip technology due to a slow uptake of smart card
reading terminals in the world market.
Smart cards have evolved significantly over the past decade and offer several advantages
compared to a general-purpose magnetic stripe card. The advantages are listed below:
Stores many times more information than a magnetic stripe card.
Reliable and harder to tamper with than a magnetic stripe card.
Performs multiple functions in a wide range of industries.
Compatible with portable electronic devices such as phones and personal digital
assistants (PDAs), and with PCs.
Stores highly sensitive data such as signing or encryption keys in a highly secure
Department of Computer Engineering,Tathwade 6
Credit Card Fraud Detection System
Manner Performs certain sensitive operations using signing or encryption keys in a secure
fashion. A consortium of Europay MasterCard and Visa (EMV) recently issued a set of
specifications for embedding chips in credit cards and processing transactions from such
cards. MasterCard and Visa have also issued deadlines for compliance with these
specifications indicating that banks will have to bear a large portion of fraud losses if
they
do not comply with EMV specifications. However, the market response has been slow so
far due to large investments needed in implementing the EMV compliant programs.
1.4 Future scope:
Credit card fraud detection system developed has very wide range of applications.
The same system can be implemented for any kind of card such as petro cards, ATM
cards, and Security Cards etc. the system has a profound future scope the system
developed uses primitive Artificial Intelligence techniques. Additional artificial
intelligence techniques such as criminal mentality may be included in the system to make
it more foolproof. Also the parameters on which the transaction fraud is detected may be
further enhanced by consulting with the banking firms to increase the efficiency of the
system. The system could also be modified as per the requirements of the concerned bank
i.e. the system could use another mode of communication such as automated police
phone dialing, mailing etc.
1.5 System description :
Credit Card Fraud is one of the biggest threats to business establishments today.
However, to combat the fraud effectively, it is important to first understand the
mechanisms of executing a fraud. Credit card fraudsters employ a large number of modus
operandi to commit fraud. In simple terms, Credit Card Fraud is defined as:
When an individual uses another individuals’ 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.
Department of Computer Engineering,Tathwade 7
Credit Card Fraud Detection System
Further, the individual using the card has no connection with the cardholder or issuer, and
has no intention of either contacting the owner of the card or making repayments for the
purchases made.
Credit card frauds are committed in the following ways:
An act of criminal deception (mislead with intent) by use of unauthorized account and/or
personal information
Illegal or unauthorized use of account for personal gain
Misrepresentation of account information to obtain goods and/or services. Contrary to
popular belief, merchants are far more at risk from credit card fraud than the cardholders.
While consumers may face trouble trying to get a fraudulent charge reversed, merchants
lose the cost of the product sold, pay chargeback fees, and fear from the risk of having
their merchant account closed. Increasingly, the card not present scenario, such as
shopping on the internet poses a greater threat as the merchant (the web site) is no longer
protected with advantages of physical verification such as signature check, photo
identification, etc. In fact, it is almost impossible to perform any of the ‘physical world’
checks necessary to detect who is at the other end of the transaction. This makes the
internet extremely attractive to fraud
Perpetrators . According to a recent survey, the rate at which internet fraud occurs is 12 to
15 times higher than ‘physical world’ fraud.
IMPACT OF CREDIT CARD FRAUDS
Unfortunately, occurrences of credit card frauds have only shown an upward trend so far.
The fraudulent activity on a card affects everybody, i.e., the cardholder, the merchant,
the acquirer as well as the issuer. This section analyses the impact that credit card frauds
have on all the players involved in transacting business through credit cards.
Impact of Fraud on Cardholders
It's interesting to note that cardholders are the least impacted party due to fraud in credit
Department of Computer Engineering,Tathwade 8
Credit Card Fraud Detection System
card transactions as consumer liability is limited for credit card transactions by the
legislation prevailing in most countries. This is true for both card-present as well as card-
not-present scenarios. Many banks even have their own standards that limit the
consumer's liability to a greater extent. They also have a cardholder protection policy in
place that covers for most losses of the cardholder. The cardholder has to just report
suspicious charges to the issuing bank, which in turn investigates the issue with the
acquirer and merchant, and processes chargeback for the disputed amount.
Impact of Fraud on Merchants
Merchants are the most affected party in a credit card fraud, particularly more in the
card-not-present transactions, as they have to accept full liability for losses due to fraud.
Whenever a legitimate cardholder disputes a credit card charge, the card-issuing bank
will send a chargeback to the merchant (through the acquirer), reversing the credit for
the transaction. In case, the merchant does not have any physical evidence (e.g. delivery
signature) available to challenge the cardholder’s dispute, it is almost impossible to
reverse the chargeback. Therefore, the merchant will have to completely absorb the cost
of the fraudulent transaction. In fact, this cost consists of several components, which
could add up to a significant amount. The cost of a fraudulent transaction consists of:
1. Cost of goods sold: Since it is unlikely that the merchandise will be recovered in a
case of fraud, the merchant will have to write off the value of goods involved in a
fraudulent transaction. The impact of this loss will be highest for low-margin
merchants.
2. Shipping cost: More relevant in a card-not-present scenario. Since the shipping cost
is usually bundled in the value of the order, the merchant will also need to absorb the
cost of shipping for goods sold in a fraudulent transaction. Furthermore, fraudsters
typically request high-priority shipping for their orders to enable rapid completion of
the fraud, resulting in high shipping costs.
Department of Computer Engineering,Tathwade 9
Credit Card Fraud Detection System
3. Card association fees: Visa and MasterCard have put in place fairly strict programs
that penalize merchants generating excessive chargebacks. Typically, if a merchant
exceeds established chargeback rates for any three-month period (e.g. 1% of all
transactions or 2.5% of the total dollar volume), the merchant could be penalized
with a fee for every chargeback. In extreme cases, the merchant’s contract to accept
cards could be terminated.
4. Merchant bank fees: In addition to the penalties charged by card associations, the
merchant has to pay an additional processing fee to the acquiring bank for every
chargeback.
5. Administrative cost: Every transaction that generates a chargeback requires
significant administrative costs for the merchant. On average, each chargeback
requires one to two hours to process. This is because processing a chargeback
requires the merchant to receive and research the claim, contact the consumer, and
respond to the acquiring bank or issuer with adequate documentation.
6. Loss of Reputation: Maintaining reputation and goodwill is very important for
merchants as excessive chargeback’s and fraud monitoring could both drive
cardholders away from transacting business with a merchant.
Impact of Fraud on Banks (Issuer/Acquirer)
Based on the scheme rules defined by both MasterCard and Visa, it is sometimes possible
that the Issuer/Acquirer bears the costs of fraud. Even in cases when the Issuer/Acquirer
is not bearing the direct cost of the fraud, there are some indirect costs that will finally be
borne by them. Like in the case of chargeback’s issued to the merchant, there are
administrative and manpower costs that the bank has to incur.
The issuers and acquirers also have to make huge investments in preventing frauds by
deploying sophisticated IT systems for detection of fraudulent transactions.
Department of Computer Engineering,Tathwade 10
Credit Card Fraud Detection System
1.6 Working of the system:
Credit card fraud detection system comprises of mainly three modules the simulator, the
fraud detection system module and sms module.
The simulator module generates random transactions this module was designed to
simulate the working of credit card swiping machine also known as terminal device. This
terminal device is registered at the service provider bank. The Credit card fraud detection
system also has client form in order to maintain and create database of this service
provider bank. Client form maintains all the necessary information of the customer r the
credit card holder. Also we can create new credit card holder accounts. The simulator
generated transactions are fed to the fraud detection system module which checks for
fraudulent transaction. In doing so this module maintains track record of each and every
credit card holder. This is termed as profile of the customer. Various other vital customer
details are maintained and updated by this module. Profile of the customer is updated at
each new transaction. Profile is nothing but the track record of the credit card usage by
the credit card holder. Simply stated it is the history of the card. The system being self
learning does not generate fraud signal if the similar transaction has already been
approved by credit card holder. If the fraud detection system module detects fraud
transaction it generates fraud signal which is fed to the sms module. The sms module
simply accepts the signal and sends sms to the respective credit card holder.
Credit Card Snapshot:
Department of Computer Engineering,Tathwade 11
Credit Card Fraud Detection System
Fig 1.Credit Card Snapshot
Here are what some of the numbers stand for:
The first digit in your credit-card number signifies the system:
3 - travel/entertainment cards (such as American Express and Diners
Club)
4 - Visa
5 - MasterCard
6 - Discover Card
The structure of the card number varies by system. For example, American
Express card numbers start with 37; Carte Blanche and Diners Club with 38.
American Express - Digits three and four are type and currency, digits
five through 11 are the account number, digits 12 through 14 are the card
number within the account and digit 15 is a check digit.
Visa - Digits two through six are the bank number, digits seven through 12
or seven through 15 are the account number and digit 13 or 16 is a check
digit.
MasterCard - Digits two and three, two through four, two through five or
two through six are the bank number (depending on whether digit two is a
1, 2, 3 or other). The digits after the bank number up through digit 15 are
the account number, and digit 16 is a check digit.
Department of Computer Engineering,Tathwade 12
Credit Card Fraud Detection System
The stripe on the back of a credit card is a magnetic stripe, often called a
magstripe. The magstripe is made up of tiny iron-based magnetic particles in a
plastic-like film. Each particle is really a tiny bar magnet about 20-millionths of
an inch long.
The general functioning of the credit card transaction is as shown below:
Fig 2. The general functioning of the credit card transaction
The model for fraud detection system is represented in the following diagram.
It must be noted that this is just a model and by no means similar to the working of our
system. It is depicted just to understand the system working.
It briefly lays the foundation of where the terminal is located or how does the bank come
into picture.
Department of Computer Engineering,Tathwade 13
Credit Card Fraud Detection System
Credit card role is depicted in the figure below:
Fig 3. Credit card role
Department of Computer Engineering,Tathwade 14
Credit Card Fraud Detection System
Authorization of transaction takes place as follows:
Fig 4. Authorization of transaction
1.3 Advantages of the system:
Credit card fraud detection will minimize economic losses of the credit card
holder.
The dealer suffers the most when credit card fraud occurs.
The dealer has to repay the customer or give him some refund.
The dealer has to pay the credit card bank the loss occurred or compensation.
The major risk of all is that the customer will never again deal with the dealer.
This may result in loss of credit in the market.
These losses may be avoided by use of this system.
The credit card company has to stop the card usage for which it needs to block
the card which adds to its expenses this may be avoided.
The credit card service provider bank needs to employ special staff to deal with
such situations hence causing unnecessary overhead. This may be avoided.
Department of Computer Engineering,Tathwade 15
Credit Card Fraud Detection System
1.7 Applications of the system:
The credit card fraud detection is applicable to security needed for any kind of card.
Though it is mainly concerned with credit card it may be applied to smart card, petro
cards, security cards, ATM cards etc. also the system to detect fraud may be used to
monitor accounts of user. The account may be of any type.
Department of Computer Engineering,Tathwade 16
Credit Card Fraud Detection System
Chapter 2
Requirement Analysis
Department of Computer Engineering,Tathwade 17
Credit Card Fraud Detection System
2 Requirement Analysis
Requirement analysis bridges the gap between system engineering and software analysis
design.
Software requirement analysis involves requirement collection, classification, structuring,
prioritizing and validation. Requirement analysis consists of two parts:
1. User Requirements
2. System Requirements
a. Functional Requirements
b. Nonfunctional Requirements
Requirements analysis of the credit card fraud detection system is as follows:
2.1 User Requirements
User Requirements specify services provided by system and constraints under
which it must operate.
The system should not cause overhead cost for sending sms.
The system should try to avoid unnecessary faults in detecting fraud.
System should be available at not too high price.
System should be compatible on existing transaction system.
System should be self learning.
System should be user friendly.
System should be automated such that it automatically sends sms to the
customer having a fraud transaction.
2.2 System Requirements
System requirements describe the system services and constraints in detail. Two types
of system requirements are:
Functional requirements
Nonfunctional requirements
Department of Computer Engineering,Tathwade 18
Credit Card Fraud Detection System
2.2.1 Functional Requirements
Functional requirements for the system describe the functionality or services that
should be provided by system functions in detail, its input and output expectation.
2.2.2 Nonfunctional Requirements
Requirements relate to whole system not to individual system feature. This means
that they are often critical than functional requirement.
2.3 Functional Requirements
Functional requirements for the system describe the functionality or services that
should be provided by system functions in detail, its input and output expectation.
Different functional requirements are listed below:
The system should support following facilities:
The system should give a pop up screen when fraud is detected.
The system should automatically send a sms to the faulty transaction credit
card holder
The transaction details of the faulty transaction should be visible.
The credit card holder must get the transaction details of the detected faulty
transaction.
2.4 Software & Hardware Requirements
2.4.1 Software Requirements
Language: c# , visual studio.net 2003
Operating System: Windows Xp
Data base : sql server.
2.4.2 Hardware Requirements
Processor: P4
RAM: 256MB
Hard Disk: 10 GB
Keyboard: 101 Keys Keyboard
Mouse: scroll mouse
Department of Computer Engineering,Tathwade 19
Credit Card Fraud Detection System
Chapter 3
System Analysis
3.1 System Enginering:
3.1.1 System goals:
Department of Computer Engineering,Tathwade 20
Credit Card Fraud Detection System
The main objectives of System analysis are-
1. Identify the customer’s needs
2. Evaluate feasibility study
3. Perform economic & technical analysis
4. Allocate functions to software, hardware, people, and database.
5. Establish cost & schedule constraints
3.1.1.1 Identify Customer’s Needs
The main purpose of this step is to identify system goals which are defined by using the
question like - what info is to be produced. What info should be provided? What
functions & performance are required?
The customer’s needs are identified to find out the features that are required for
system’s success.
The system should try to detect out of track transactions.
The response time of the system should be minimal.
Customer should not have too much overhead cost for operating the
system.
The system should be user friendly.
The system should be foolproof enough so as not to create nuisance to the
card holder.
The customer details like address, phone no., and other details are
required.
The system also needs various other data such as assets owned by the
customer in order to have a rough background of the economic condition
of the customer.
3.1.1.2 Feasibility Study
It is necessary to evaluate feasibility of a project. Four primary areas for feasibility study
are:
a. Economic Feasibility
b. Technical Feasibility
Department of Computer Engineering,Tathwade 21
Credit Card Fraud Detection System
c. Legal Feasibility
d. Alternatives
3.1.3.Project Cost & Performance
Hardware Requirement:
P4 (Pentium IV) or higher processor
RAM - minimum 256MB RAM
HDD - minimum 10 GB or more of free Hard-disk space
Cell phone – Nokia with data cable compatible
Software Requirement:
Operating System - WINDOWS Xp
Database - SQL SERVER
Visual Studio .NET
3.1.4 Alternatives:
Such kind of system is not available in Indian Software Market.
3.3 System Analysis
Feasibility Study
It is necessary to evaluate feasibility of a project. Four primary areas for feasibility study
are:
a. Economic Feasibility
b. Technical Feasibility
c. Legal Feasibility
d. Alternatives
a. Economic Feasibility
This involves the study of cost benefit analysis.
The system will reside on the already existing bank server which will trace on
every incoming fraud. Hence operation cost of the system will be negligible
compared with the benefits as only RAM of the server will have to be enhanced to
Department of Computer Engineering,Tathwade 22
Credit Card Fraud Detection System
higher power in proportion of the traffic of transactions. Also development cost of
the system is bearable by the bank compared to the losses it has to suffer.
This system will save vital customer money. Also the dealers will not get affected
adding to the economic value of the system.
b. Technical Feasibility
During technical feasibility analyst evaluates technical merits of the system
concept, and at the same time collects information about performance, reliability,
maintainability.
The system is also technically feasible as variety of languages are available for
development like VC++, VB ,ASP ,C,C++,JAVA etc. databases such as DB2,
oracle could also have been used.
c. Allocation and Trade-offs
Each system function with its performance and interface characteristics is
allocated to one or more system elements.
The user interface is required to deal with entry and maintain accounts of the card
holders.
The sms module requires data cable enabled cell phone connected to the USB of
the computer in use.
Department of Computer Engineering,Tathwade 23
Credit Card Fraud Detection System
Chapter 4
System Design
4.System Design:System design can be classified into two parts namely:
Data Flow Diagrams UML(Unified Modeling Language) Diagrams
Department of Computer Engineering,Tathwade 24
Credit Card Fraud Detection System
4.1 Data Flow Diagram (DFD)
This section of report gives the dataflow of the system with the help of dataflow
diagrams as given below. Thus helping us to get knowledge of how the data in the
system flows and how interaction between them takes place.
4.1.1 DFD Level ‘0’:
Fig 5. DFD Level ‘0’
5.1.2 DFD Level ‘1’:
Department of Computer Engineering,Tathwade 25
Bank Server SMS System
System Db Display
C.C.F.D. System
Credit Card Fraud Detection System
Fig 6. DFD Level ‘1’
4.2 Unified Modeling Language:
Department of Computer Engineering,Tathwade 26
Credit Card Fraud Detection System
The Unified Modeling Language (UML) is a graphical language for visualizing,
specifying, constructing, and documenting the artifacts of a software intensive system. It
is very expressive language, addressing all the views needed to develop and then deploy
such systems. Following section shows different UML diagrams for Magic Image
Processor system itself, and different modules of system such as Image Resize, Image
Transformation, Image Enhancement, and Color Space Conversion.
4.2.1 UML Diagrams for Magic Image Processor System
4.2.1 Use Case Diagram
A use case diagram is a graph of actors, a set of use cases enclosed by a system boundary,
communication (participation) associations between the actors and the use cases, and
generalizations among the use cases.
Use case diagrams allow you to capture business events by analyzing how objects
external to the system interact with the system. A use case diagram represents a particular
sequence of transactions between the system and an actor (an end user or system external
to the system being analyzed). You can use case diagrams to analyze system
requirements and to help you define system boundaries.
Use case diagram for simulator:
simulator
simulates transaction
generates random place/terminal id
<<extern>>
generates random card no
<<extern>>
generates item according to terminal id
amount according to item
<<extend>>
<<extend>>
Department of Computer Engineering,Tathwade 27
Credit Card Fraud Detection System
Figno 11. Use case diagram for simulator
Use case diagram for fraud detection system:
validate transaction check card limit & balance
<<extend>>
fraud alert evaluate fraud meter
<<extend>>
Fraud detection sys
initiate SMS system send SMS
<<extern>>
Figno 12. Use case diagram for fraud detection system
Use case diagram for administrator:
Department of Computer Engineering,Tathwade 28
Credit Card Fraud Detection System
create place table
create profile table
create item & amount table
Admincreate new account
<<extern>>
<<extern>>
<<extern>>
Figno 13. Use case diagram for administrator:
4.2.2 Component Diagram
It shows the organizations and dependencies among a set of components.
Component is a replaceable part of a system.
Components can be packed logically.
It conforms to a set of interfaces.
It provides the realization of an interface
It represents a physical module of code.
Component diagram for Credit Card Fraud Detection System:
Department of Computer Engineering,Tathwade 29
Credit Card Fraud Detection System
Figno 17. Component diagram for Credit Card Fraud Detection System
4.2.3 Class Diagram
A class diagram shows the existence of classes and their relations in the logical view of a
system. It shows
a) UML modeling elements in class diagram
b) Classes and their structure and behavior
c) Associations, aggregation, dependency, and inheritance relationships
d) Multiplicity and navigation indicators
e) Role names
Department of Computer Engineering,Tathwade 30
credit card.data
credit card.log
simulator.cs
client.cs
fraud_pop_up.cs
SMS_send.cs
main.cs
generate transaction
display fraudulent transaction
create new account
send SMS to card owner
Credit Card Fraud Detection System
Validation
user_name : charPassword : sp.char
validate_user()grant_access_authority()
provides terminal id of particular place
place table
place_name : charterminal_id : int
get_palce()Display_place()display_terminal_id()modify()provide_info()
provides avilabe info on item to particuular terminal
item table
terminal_id : intitem_no : intitem : chardealer_type : char
get_item()get_dealer_type()provide_info()
provides the ammount of particular item
amount table
item_no : intamount : double
get_amount()provide_info()
simulate transaction
credit_card_no : intplace : charitem : charamount : doubledate_time : datetime
genrate_trans()display_trans()save_trans()get_msguser()
<<amount of item>>
<<item & dealer type>>
<<teminal id & place>>
simulates real world transaction for random credit card
provides credit card holders info
client info
credit_card_no : intname : charphone_no : intaddress : chare-mail_add : charoccupation : charnationality : charincome : intgender : charmarital_st : charassets : charfev : charcard_type : charcredit_limit : int
get_info()provid_info()manage_limit()create_place_table()create_item_table()create_ammount_table()
<<client info>>
Figno 7 - Class diagram for Simulator
Department of Computer Engineering,Tathwade 31
Credit Card Fraud Detection System
Class diagram for Fraud Detection System :
Department of Computer Engineering,Tathwade 32
Credit Card Fraud Detection System
genrates transaction
simulate transaction
credit_card_no : intplace : charitem : charamount : doubledate_time : datetime
genrate_trans()display_trans()save_trans()get_msguser() provides client info
client info
credit_card_no : intname : charphone_no : intaddress : chare-mail_add : charoccupation : charnationality : charincome : intgender : charmarital_st : charassets : charfev : charcard_type : charcredit_limit : int
get_info()provid_info()manage_limit()create_place_table()create_item_table()create_amount_table()
maintains most probable transaction record for each client
entity set
palce_table_card_no : tableitem_table_card_no : tableamont_avg : double
create_tables()update_entity_set()delete_entity_set()
+1
+1
detects fraudulent transaction
fraud detection system
trans_palce : chartrans_ammount : doubletrans_item : chartrans_datetime : datetimecard_no : intdealertype : char
detect_fradulent_trans()inform_sms_sys()unsave_fraudulent_trans()upgrade_AI_for_faulty_fraud_detection()
<<transaction>><<client info(card no,add)>>
<<probablistic trans detail...
informs SMS system
keeps latest transaction as profile
profile
trans_palce : chartrans_item : chartrans_ammount : doubletrans_datetime : datetimebalance_limit : double
maintain_latest_transaction()
<<profile>>
Figno 8. Class diagram for Fraud Detection System
Class diagram for Messaging System :
Department of Computer Engineering,Tathwade 33
Credit Card Fraud Detection System
informs SMS systemdetects fraudulent transaction
fraud detection system
trans_palce : chartrans_ammount : doubletrans_item : chartrans_datetime : datetimecard_no : intdealertype : char
detect_fradulent_trans()inform_sms_sys()unsave_fraudulent_trans()upgrade_AI_for_faulty_fraud_detection()
sends sms to appropriate card owner
SMS system
fraudulent_trans_palce : charfraudulent_trans_item : charfraudulent_trans_ammount : doublefraudulent_trans_datetime : datetimeclient_phone_no : intmessage_format : char
send_sms_client_phone_no()
<<fraudulent transaction>>
Figno 9. Class diagram for Messaging System
Class Diagram For Client Information:
Department of Computer Engineering,Tathwade 34
Credit Card Fraud Detection System
provides client info
creates place info tablecreates item info table
client info
credit_card_no : intname : charphone_no : intaddress : chare-mail_add : charoccupation : charnationality : charincome : intgender : charmarital_st : charassets : charfev : charcard_type : charcredit_limit : int
get_info()provid_info()manage_limit()create_place_table()create_item_table()create_amount_table()
creates ammount info table
Figno10. Class Diagram For Client Information
Department of Computer Engineering,Tathwade 35
Credit Card Fraud Detection System
4.2.4 Sequence Diagram
Interaction Diagram
A pattern of interaction among objects is shown on an interaction diagram. Interaction
diagrams come in two forms based on the same underlying information but each
emphasizing a particular aspect of it:
1. Sequence diagrams
2. Collaboration diagrams.
A sequence diagram shows an interaction arranged in time sequence. In particular, it
shows the objects participating in the interaction by their "lifelines" and the messages that
they exchanged arranged in time sequence. It does not show the associations among the
objects.
A collaboration diagram shows an interaction organized around the objects in the
interaction and their links to each other. Unlike a sequence diagram, a collaboration
diagram shows the relationships among the objects. On the other hand, a collaboration
diagram does not show time as a separate dimension, so the sequence of messages and
the concurrent threads must be determined using sequence numbers.
Department of Computer Engineering,Tathwade 36
Credit Card Fraud Detection System
Sequence diagram for credit card fraud detection system:
simulator fraud detection system
Message sending system
generate new transaction
check for fraudulent transaction
if non-fraudulent - save transaction
inform simulator
display transaction
if fraudulent initiate SMS system
send SMS to appropriate card owner
alert fraud
display fraudulent transaction
Figno 14.Sequence diagram for credit card fraud detection system
Collaboration diagram for credit card fraud detection system:
Message sending system
simulator
fraud detection system
2: check for fraudulent transaction3: if non-fraudulent - save transaction
5: display transaction8: display fraudulent transaction 9: send SMS to appropriate card owner
1: generate new transaction
4: inform simulator7: alert fraud
6: if fraudulent initiate SMS system
Department of Computer Engineering,Tathwade 37
Credit Card Fraud Detection System
Figno 15. Collaboration diagram for credit card fraud detection system
5.2.5 Activity Diagram
An activity diagram is a special case of a state diagram in which all of the states are
action states and most of the transitions are triggered by completion of the actions in the
source states. The purpose of this diagram is to focus on flows driven by internal
processing. They are useful for showing workflow and parallel processing.
Activity diagram for Credit Card Fraud Detection System:
simulate transaction
update entire entity set for card no
display transaction
dislpay transaction information
check for fraud
save transaction
if non-frudulent
send SMS
get Phone no from client information
send sms to the received no
get Phone no from client information
send sms to the received no
If fraudulent
SMS systemfraud detection systemsimulator
Figno 16. Activity diagram for Credit Card Fraud Detection System
Department of Computer Engineering,Tathwade 38
Credit Card Fraud Detection System
5.2.1.6 Deployment Diagram
Deployment diagrams show the configuration of run-time processing elements and the
software components, processes, and objects that live on them. Software component
instances represent run-time manifestations of code units. Components that do not exist
as run-time entities (because they have been compiled away) do not appear on these
diagrams; they should be shown on component diagrams.
Deployment diagram for Credit Card Fraud Detection System:
sql server data base
simulator
fraud detection system
message sending system
GSM mobile device
Figno18. Deployment diagram for Credit Card Fraud Detection System
Department of Computer Engineering,Tathwade 39
Credit Card Fraud Detection System
Chapter 3
References
Department of Computer Engineering,Tathwade 40
Credit Card Fraud Detection System
References:
Books:
1) C# programming – Wrox publication
2) C# in 21 days – SAMS publication.
3) Learning C# – by Maurch
4) S. Ghosh and D. L. Reilly "Credit card fraud detection with a neural network", in Proc. 27th Hawaii Int. Conf. Syst. Sci., pp. 621-630. 1994.
Websites:
Credit / Debt Managementhttp://credit.about.com/cs/fraud/
Duncan M D G. 1995. The Future Threat of Credit Card Crime, RCMP Gazette, 57 (10): 25–26.P Chan, W Fan, A Prodromidis & S Stolfo. 1999. Distributed data mining in credit card fraud detection, IEEE Intelligent Systems, 14(6): 67–74. 2001. Fraud Prevention Reference Guide, Anonymous, Certegy, September 2001. Bill Rini. 2002.White Paper on Controlling Online Credit Card Fraud, Window Six, January 2002. http://www.windowsix.com
www.mastercsharp.com
www.wrox.com
www.americanexpress.com
www.mastercard.com
www.visa.com
www.activexperts.com
Department of Computer Engineering,Tathwade 41
Credit Card Fraud Detection System
www.microsoft.com
www.forum.nokia.com
www.developer’shome.com
www.orkut.com
Department of Computer Engineering,Tathwade 42