CREDIT CARD FRAUD DETECTION USING HIDDEN MARKOV MODEL

BY S.Srilakshmi Ramya, Mtech(CSE), 09M81D5812.

ABSTRACT
Now a day the usage of credit cards has dramatically increased. As credit card becomes the most popular mode of payment for both online as well as regular purchase, cases of fraud associated with it are also rising. In this paper, we model the sequence of operations in credit card transaction processing using a Hidden Markov Model (HMM) and show how it can be used for the detection of frauds. An HMM is initially trained with the normal behavior of a cardholder. If an incoming credit card transaction is not accepted by the trained HMM with sufficiently high probability, it is considered to be fraudulent. At the same time, we try to ensure that genuine transactions are not rejected. We present detailed experimental results to show the effectiveness of our approach and compare it with other techniques available in the literature.

INTRODUCTION
Credit-card-based purchases can be categorized into two types: 1) Physical card and 2) Virtual card. 1) Physical card: In a physical-card based purchase, the cardholder presents his card physically to a merchant for making a payment. To carry out fraudulent transactions in this kind of purchase, an attacker has to steal the credit card.

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. secure code) is required to make the payment. .2) Virtual card: In the second kind of purchase. expiration date. only some important information about a card (card number.

EXISTING SYSTEM • In case of the existing system the fraud is detected after the fraud is done that is. • And so the card holder faced a lot of trouble before the investigation finish. To avoid the entire above disadvantage we propose the system to detect the fraud in a best and easy way. • And also now a days lot of online purchase are made so we don’t know the person how is using the card online. we just capture the IP address for verification purpose. we need to maintain a huge data.And also as all the transaction is maintained in a log. • So there need a help from the cyber crime to investigate the fraud. the fraud is detected after the complaint of the card holder. .

we present a Hidden Markov Model (HMM). . and the issuing bank declines the transaction. • The details of items purchased in Individual transactions are usually not known to any Fraud Detection System (FDS) running at the bank that issues credit cards to the cardholders.Which does not require fraud signatures and yet is able to detect frauds by considering a cardholder’s spending habit. • If the FDS confirms the transaction to be of fraud.PROPOSED SYSTEM • In proposed system. • An FDS runs at a credit card issuing bank. it raises an alarm. Each incoming transaction is submitted to the FDS for verification.

Advantages 1) The detection of the fraud use of the card is found much faster that existingsystem. 3) The log which is maintained will also be a proof for the bank for the transaction made. 2) In case of the existing system even the original card holder is also checked for frauddetection. But in this system no need to check the original user as we maitain a log. 4) We can find the most accurate detection using this technique. .

A complete system has been implemented for this purpose. These transactions contain example fraud cases due to lost cards. stolen cards.LITERATURE SURVEY Ghosh and Reilly have proposed credit card fraud detection with a neural network. mail-order fraud. Recently. . application fraud Counterfeit fraud. Syeda et al. They have built a detection system. which is trained on a large sample of labeled credit card account transactions. have used parallel granular neural networks (PGNNs) for improving the speed of data mining and knowledge of discovery process in credit card fraud detection. and non received issue (NRI) fraud.

. We denote the set of symbols V ={v1.O3. . . S2. 1<j< N. j.ALGORITHM An HMM Model can be characterized by the following : 1. 4. where Si. 2. The observation sequence O = O1. 1<i<N.The state transition probability matrixA =[aij]. where aij=P(qt+1=Sj|qt=Si). . . VM}. where bj(k)=P(Vk|Sj). . 1<k<M 5. The observation symbols correspond to the physical output of the system being modeled. . 2. whereVi. 2. and R is the number of observations in the sequence. . i =1. .O2. . V2. The observation symbol probability matrix B =[bj(k). . The state at time instant t is denoted by qt.OR. 1<j<N. 2. SN]. . 3. . where each observation Ot is one of the symbols from V. . We denote the set of states S =[S1.N is an individual state. ..N is the number of states in the model. i = 1. . . . . we have aij >0 for all i. M is the number of distinct observation symbols per state. . t=1.For the general case where any state j can be reached from any other state i in a single step.M is an individual symbol.

SYSTEM ANALYSIS & DESIGN Use case diagram New Card User Login Store Info Verification Transaction .

Module diagram Start New Card Login Security Information Transaction Verification Stop .

System Architecture User Login Details Login Account Details Transaction Verification Complete n Security .

Project Flow Diagram User Account Area Start Transaction Verification User Security User .

Class diagram .

State diagram .

Pay Verification Complete Transaction .Activity diagram New Account Security Yes Account CheckSec No Login. Purchase.

Sequence diagram New Account User Info Login Transaction Verification Security Complete Transaction Login Info Transaction Details Security Info Verification Details .

Collaboration diagram New Account 1: User Info Login Complete Transaction 2: Login Info 5: Verification Details Transaction 3: Transaction Details Verification 4: Security Info Security .

Net 2. Visual C# . : : : : : Pentium IV 2.4 GHz 40 GB 15 VGA colour Logitech.Net SQL Server 2005.IMPLEMENTATION System Requirements : Hardware Requirements: SYSTEM HARD DISK MONITOR MOUSE RAM Software Requirements: Operating system Front End Coding Language Back-End : : : : Windows XP Professional Asp . 256 MB .0.

List of Modules 1. Verification .Transaction 5. New Card 2. Login 3. Security information 4.

Which additional resources they will have access to can be configured separately. . If the card lost then the Security information module form arise. The information is all about there contact details. 2)Login:Login Form module presents site visitors with a form with user name and password fields. the customer gives there information to enrol a new card.Module Description 1)New card:In this module. They can create there own login and password for there future use of the card. 3)Security information:In Security information module it will get the information detail and its store’s in database. If the user enters a valid username/password combination they will be granted access to additional resources on website. It has a set of question where the user has to answer the correctly to move to the transaction section.

based on confidential information in the possession of the initiating party. verifying party. and storing therein.Continue… 4)Transaction:- The method and apparatus for pre-authorizing transactions includes providing a communications device to a vendor and a credit card owner. a distinguishing piece of information that characterizes a specific transaction to be made by an authorized user of the credit card at a later time. the verification information being given by a third. . 5)Verification:- Verification information is provided with respect to a transaction between an initiating party and a verification-seeking party. The credit card owner initiates a credit card transaction by communicating to a credit card number.

The .NET Server.NET and Windows. .NET” is also the collective name given to various software components built upon the . and Web solutions. for instance) and services (like Passport.NET FRAMEWORK : 1. 2.Net: Microsoft .NET Framework is a language-neutral platform for writing programs that can easily and securely interoperate. “.NET is a set of Microsoft software technologies for rapidly building and integrating XML Web services.NET My Services. .NET platform.The Common Language Runtime (CLR). The . Microsoft Windows-based applications.NET Framework class library. and so on).Software Description Features of . COMPONENTS OF . These will be both products (Visual Studio.

code safety verification.compilation. • • • • Security Robostness Productivity Performance .and remoting and also ensures more security and robustness. FEATURES OF THE COMMON LANGUAGE RUNTIME(CLR): The Common Language Runtime manages memory.The Common Language Runtime (CLR): The CLR is described as the “execution engine” of .NET. execution. providing important services such as memory management.1.That means it manages code at execution time.thread execution.and other system Services these are all run on CLR.

NET provides a single-rooted hierarchy of classes. Boolean.The .The class library is subdivided into a number of sets (or namespaces). XML SUPPORT: Extensible Markup Language(XML) provides a method for describing structured data. as well as Object.2. The root of the namespace is called System.NET Framework class library: .XML is asubset of SGML that is optimized for delivery over the web. this contains basic types like Byte. and String. Double. .providing the XML designer to make it easier to edit XML and create XML schemas. each providing distinct areas of functionality.NET fully supports XML.The World Wide Web Consortium(w3c) defines XML standards so that structured data will be uniform and independent of applications.Visual Studio . containing over 7000 types. with dependencies between the namespaces kept to a minimum.

Home page .

Login page .

Transaction page .

Admin page .

sub assemblies. Testing is the process of trying to discover every conceivable fault or weakness in a work product.TESTING The purpose of testing is to discover errors. assemblies and/or a finished product It is the process of exercising software with the intent of ensuring that the Software system meets its requirements and user expectations and does not fail in an unacceptable manner. Unit testing: Unit testing involves the design of test cases that validate that the internal program logic is functioning properly. and that program inputs produce valid outputs. It is the testing of individual software units of the application . It provides a way to check the functionality of components. There are various types of test. All decision branches and internal code flow should be validated. Each test type addresses a specific testing requirement.

It tests a configuration to ensure known and predictable results. and user manuals. System Testing: System testing ensures that the entire integrated software system meets requirements. An example of system testing is the configuration oriented system integration test. . Testing is event driven and is more concerned with the basic outcome of screens or fields. system documentation. Functional Testing: Functional tests provide systematic demonstrations that functions tested are available as specified by the business and technical requirements.Integration testing: Integration tests are designed to test integrated software components to determine if they actually run as one program.

such as specification or requirements document. structure and language of the software. structure or language of the module being tested. Black box tests. such as specification or requirements document. or at least its purpose. must be written from a definitive source document. Black Box Testing: Black Box Testing is testing the software without any knowledge of the inner workings. .White Box Testing: White Box Testing is a testing in which in which the software tester has knowledge of the inner workings. as most other kinds of tests. It is purpose. It is used to test areas that cannot be reached from a black box level.

merchants and other businesses who operate on the Web. this is not a hard and fast rule. Internal security measures are usually more expensive than those that are outsourced. it becomes difficult to maintain a secure environment for credit card processing. With these new threats constantly undermining the security measures in place.SECURITY Investing In Security: According to Symantec. The cost effectiveness of higher security depends on where the security is found. . This is an ongoing issue for those working to provide a secure environment for consumers. giving e-commerce merchants an affordable option without increasing the chance of security being breached. for every second last year. nine new threats were unleashed onto the Web. Security Doesn’t Have To Break The Bank: While it is definitely implied that the better the security provided by the processor the more expensive the fees.

as well as application of this knowledge in deciding the value of observation symbols and initial estimate of the model parameters.CONCLUSION • • • • • • In this paper. The different steps in credit card transaction processing are represented as the underlying stochastic process of an HMM. whereas the types of item have been considered to be states of the HMM. We have suggested a method for finding the spending profile of cardholders. we have proposed an application of HMM in credit card fraud detection. It has also been explained how the HMM can detect whether an incoming transaction is fraudulent or not. Experimental results show the performance and effectiveness of our system and demonstrate the usefulness of learning the spending profile of the cardholders . We have used the ranges of transaction amount as the observation symbols.

In future we can prepare an application with consistent Fraud Detection with new techniques and modules. we can develop a sophisticated modules like calculating Fraud Timings. capturing the photo of the Fraud and many more modules can be developed . some effective algorithm which can perform well for the classification problem with variable missclassification costs could be developed.FUTURE ENHANCEMENTS The findings obtained here may not be generalized to the global fraud detection problem. As future work.

.Thanq….

Sign up to vote on this title
UsefulNot useful

Master Your Semester with Scribd & The New York Times

Special offer for students: Only $4.99/month.

Master Your Semester with a Special Offer from Scribd & The New York Times

Cancel anytime.