Survey on Credit Card Fraud Detection Methods

Transcription

1 Survey on Credit Card Fraud Detection Methods Krishna Kumar Tripathi 1, Mahesh A. Pavaskar 2 1 Computer Engg., M.E Computer, TERNA Engg College NERUL, Mumbai University, Mumbai, Maharashtra, India. 2 Computer Engg., M. Tech Computer, VJTI, Mumbai University, Mumbai, Maharashtra, India. Abstract Due to a rapid advancement in the electronic commerce technology, the use of credit cards has increased. As credit card becomes the most popular mode of payment for both online as well as regular purchase, cases of credit card fraud also rising. Financial fraud is increasing significantly with the development of modern technology and the global superhighways of communication, resulting in the loss of billions of dollars worldwide each year. The fraudulent transactions are scattered with genuine transactions and simple pattern matching techniques are not often sufficient to detect those frauds accurately. Implementation of efficient fraud detection systems has thus become imperative for all credit card issuing banks to minimize their losses. Many modern techniques based on Artificial Intelligence, Data mining, Neural Network, Bayesian Network, Fuzzy logic, Artificial Immune System, K- nearest neighbor algorithm, Support Vector Machine, Decision Tree, Fuzzy Logic Based System, Machine learning, Sequence Alignment, Genetic Programming etc., has evolved in detecting various credit card fraudulent transactions. This paper presents a survey of various techniques used in credit card fraud detection mechanisms. Keywords Credit card fraud, Credit Card Fraud detection methods, Electronic Commerce. A. Problem Definition I. INTRODUCTION An e-commerce payment system facilitates the acceptance of electronic payment for online transactions. Also known as a sample of Electronic Data Interchange (EDI), e-commerce payment systems have become increasingly popular due to the widespread use of the internet-based shopping and banking. Since in traditional systems the fraud is detected only when the billing for credit card is done, it is very difficult to prevent fraudulent transactions. B. Types of Frauds Various types of frauds in this paper include credit card frauds, telecommunication frauds, and computer intrusions, Bankruptcy fraud, Theft fraud/counterfeit fraud, Application fraud, Behavioral fraud [20]. Credit Card Fraud: Credit card fraud has been divided into two types: Offline fraud and On-line fraud. Offline fraud is committed by using a stolen physical card at call center or any other place. On-line fraud is committed via internet, phone, shopping, web, or in absence of card holder. Telecommunication Fraud: The use of telecommunication services to commit other forms of fraud. Consumers, businesses and communication service provider are the victims. Computer Intrusion: Intrusion Is Defined As The Act Of Entering Without Warrant Or Invitation; That Means Potential Possibility Of Unauthorized Attempt To Access Information, Manipulate Information Purposefully. Intruders May Be From Any Environment, An Outsider (Or Hacker) And An Insider Who Knows The Layout Of The System [7]. Bankruptcy Fraud: This column focuses on bankruptcy fraud. Bankruptcy fraud means using a credit card while being absent. Bankruptcy fraud is one of the most complicated types of fraud to predict [7]. Theft Fraud/ Counterfeit Fraud: In this section, we focus on theft and counterfeit fraud, which are related to one other. Theft fraud refers using a card that is not yours. As soon as the owner give some feedback and contact the bank, the bank will take measures to check the thief as early as possible. Likewise, counterfeit fraud occurs when the credit card is used remotely; where only the credit card details are needed [20]. Application Fraud: When someone applies for a credit card with false information that is termed as application fraud. For detecting application fraud, two different situations have to be classified. When applications come from a same user with the same details, that is called duplicates, and when applications come from different individuals with similar details, that is termed as identity fraudsters. Phua et al. (2006) describes application fraud as demonstration of identity crime, occurs when application form(s) contain possible, and synthetic (identity fraud), or real but also stolen identity information (identity theft). 721

2 In most of the banks, eligibility for a credit card, applicants need to complete an application form. Application form is mandatory except for social fields. The bank would also ask for certain details as contact details, such as address, mobile phone number and land-line number. Confidential information will be the password [7] [20]. Behavioral Fraud: Behavioral fraud occurs when sales are made on a cardholder present basis and details of legitimate cards have been obtained fraudulent basis [7][20]. C. Credit Card Fraud Detection Methods On doing the literature survey of various methods for fraud detection we come to the conclusion that to detect credit card fraud there are multiple approaches like[8][9][20]. A Fusion Approach Using Dempster-Shafer Theory and Bayesian Learning. Blast-Ssaha Hybridization Hidden Markov Model. Neural Network Bayesian Network Genetic Algorithm Artificial Immune System K- nearest neighbor algorithm Support Vector Machine Decision Tree Fuzzy Logic Based System Meta Learning Strategy II. A FUSION APPROACH USING DEMPSTER-SHAFER THEORY AND BAYESIAN LEARNING. As mentioned in [1] First approach i.e. Dempster-Shafer Theory basically proposes Fraud Detection System using information fusion and Bayesian learning in which evidences from current as well as past behavior are combined together and depending on certain type shopping behavior establishes an activity profile for every cardholder. It has advantages like: - high accuracy, processing speed, reduces false alarm, improves detection rate, applicable in E-commerce. But one disadvantage of this approach is that it is highly expensive. Fig. 1 Block diagram of the Fraud Detection System [8] Dempster Shafer theory and Bayesian learning is a hybrid approach for credit card fraud detection [8][9][20] which combines evidences from current as well as past behavior. Every cardholder has a certain type of shopping behavior, which establishes an activity profile for them. This approach proposes a fraud detection system using information fusion and Bayesian learning of so as to counter credit card fraud. The FDS system consists of four components, namely, rule-based filter, Dempster Shafer adder, transaction history database and Bayesian learner. In the rule-based component, the suspicion level of each incoming transaction based on the extent of its deviation from good pattern is determined. Dempster Shafer s theory is used to combine multiple such evidences and an initial belief is computed [5]. Then the initial belief values are combined to obtain an overall belief by applying Dempster Shafer theory. The transaction is classified as suspicious or suspicious depending on this initial belief. Once a transaction is found to be suspicious, belief is further strengthened or weakened according to its similarity with fraudulent or genuine transaction history using Bayesian learning [8]. It has high accuracy and high processing Speed. It improves detection rate and reduces false alarms and also it is applicable in E-Commerce. But it is highly expensive and its processing Speed is low. 722

3 III. International Journal of Emerging Technology and Advanced Engineering BLAST-SSAHA HYBRIDIZATION As the name suggest Blast-Ssaha Hybidization [2] is a hybridization of BLAST and SSAHA algorithms which is referred as BLAH-FDS algorithm. This algorithm is basically the efficient two-stage sequence alignment algorithm which is used for analyzing spending behavior of customers. The performance of this algorithm is good, also accuracy is high. It is useful in telecommunication and banking fraud detection and processing speed is also high. But disadvantage is that it does not detect cloning of credit cards [9]. A Hidden Markov Model is a double embedded stochastic process which is used to model much more complicated stochastic processes as compared to a traditional Markov model. If 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. A Hidden Markov Model [23] is initially trained with the normal behavior of a cardholder. It works on the user spending profiles which can be divided into three types such as 1) Lower profile; 2) Middle profile; and 3) Higher profile [9]. V. NEURAL NETWORK & BAYESIAN NETWORK Bayesian and Neural network approach is automatic credit card fraud detection system and type of artificial intelligence programming which is based on variety of methods including machine learning approach, supervised and data mining for reasoning under uncertainty. The advantage of neural network is that it learns and does not need to be reprogrammed. Its processing speed is higher than Bayesian neural networks but it needs high processing time for large neural networks. Whereas Bayesian neural networks provide good accuracy but needs training of data to operate and requires high processing speed [8][9]. Fig. 2 Architecture of BLAST and SSAHA Fraud Detection System [8] IV. HIDDEN MARKOV MODEL A Hidden Markov Model is a double embedded stochastic process with used to model much more complicated stochastic processes as compared to a traditional Markov model. If 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. HMM[3], Baum Welch algorithm is used for training purpose and K-means algorithm for clustering.hmm sores data in the form of clusters depending on three price value ranges low, medium and high[10]. The probabilities of initial set of transaction have chosen and FDS checks whether transaction is genuine or fraudulent. Since HMM maintains a log for transactions it reduces tedious work of employee but produces high false alarm as well as high false positive[4]. Fig. 3 Layer of Neural Network in Credit Card [15]. Neural Network can uses following approach [9]: I) Back propagation neural network II) Self Organizing Map 723

4 VI. International Journal of Emerging Technology and Advanced Engineering GENETIC ALGORITHM Genetic algorithms, inspired from natural evolution were first introduced by Holland (1975). Genetic algorithms are evolutionary algorithms which aim at obtaining better solutions as time progresses. Fraud detection problem is classification problem, in which some of statistical methods many data mining algorithms have proposed to solve it. Among decision trees are more popu-lar. Fraud detection has been usually in domain of E-commerce, data mining [11]. GA is used in data mining mainly for variable selection [24] and is mostly coupled with other DM algorithms [25]. And their combination with other techniques has a very good performance. GA has been used in credit card fraud detection for minimizing the wrongly classified number of transactions [25]. And is easy accessible for computer programming language implementation, thus, make it strong in credit card fraud detection. But this method has high performance and is quite expensive. VII. ARTIFICIAL IMMUNE SYSTEM Artificial immune systems (AIS) represent an important strategy inspired by biological systems and developed by Neal et al in 1998 [26]. The main developments within AIS have focused on three main immunological theories: clonal selection, immune networks and negative selection. The immune system can distinguish between self and non-self. In the concept of credit card fraud detection, self (S) represents all patterns in a finite space that is legitimate and non-self (Ŝ) represents all patterns that are not in self [27][28]. The AIS consists of artificial lymphocytes (ALCs) that able to classify any pattern as self or non-self by detecting only non-self patterns. AIS detection engines implements AIS based algorithms which can classify input data as normal or fraudulent [12]. VIII. K- NEAREST NEIGHBOR ALGORITHM The concept of credit card fraud detection by using a data stream outlier detection algorithm which is based on reverse k-nearest neighbors (SODRNN). The distinct quality of SODRNN algorithm is it needs only one pass of scan. Whereas traditional methods need to scan the database many times, it is not suitable for data stream environment [16]. The performance of KNN algorithm is influenced by three main factors [Mohammed J. Islam]: 724 The distance metric used to locate the nearest neighbors. The distance rule used to derive a classification from k- nearest neighbor. The number of neighbors used to classify the new sample. IX. SUPPORT VECTOR MACHINE The basic idea of SVM classification algorithm is to construct a hyper plane as the decision plane which making the distance between the positive and negative mode maximum [18]. The strength of SVMs comes from two important properties they possess - kernel representation and margin optimization. Kernels, such as radial basis function (RBF) kernel, can be used to learn complex regions. A kernel function represents the dot product of projections of two data points in a high dimensional feature space. In SVMs, the classification function is a hyper-plane separating the different classes of data. The basic technique finds the smallest hypersphere in the kernel space that contains all training instances, and then determines on which side of hypersphere a test instance lies. If a test instance lies outside the hypersphere, it is confirmed to be suspicion SVM can have better prediction performance than BPN(Back propagation network ) in predicting the future data. But in large data BPN has a good performance. X. DECISION TREE Decision trees are statistical data mining technique that express independent attributes and a dependent attributes logically AND in a tree shaped structure. Classification rules, extracted from decision trees, are IF-THEN expressions and all the tests have to succeed if each rule is to be generated [8]. Decision tree usually separates the complex problem into many simple ones and resolves the sub problems through repeatedly using [8][17]. Decision trees are predictive decision support tools that create mapping from observations to possible consequences. There are number of popular classifiers construct decision trees to generate class models. Decision tree methods C5.0,C&RT and CHAID.The work demonstrates the advantages of applying the data mining techniques including decision trees and SVMs to the credit card fraud detection problem for the purpose of reducing the bank s risk. The results show that the proposed classifiers of C&RT and other decision tree approaches outperform SVM approaches in solving the problem under investigation.

5 However, as the size of the training data sets become larger, the accuracy performance of SVM based models reach the performance of the decision tree based models, but the number of frauds caught by SVM models are still far less than the number of frauds caught by decision tree methods, especially C&RT model[17]. XI. A. Fuzzy Neural Network FUZZY LOGIC BASED SYSTEM The aim of FNNs is to process the massive volume of uncertain information, which is widespread applied in our life [9]. Syeda et al (2002) [8] propose fuzzy neural networks on parallel machines to speed up rule production for customer-specific credit card fraud detection. B. Fuzzy Darwinian System Fuzzy Darwinian Detection [21] is Evolutionary-Fuzzy system which uses genetic programming for evolving fuzzy logic rules. It classifies the transactions into suspicious and non-suspicious. It comprises of Genetic Programming (GP) search algorithm and a fuzzy expert system. This approach has very high accuracy and produces a low false alarm. But it is not applicable in online transactions. Also it is highly expensive and processing speed is low.[8] XII. CONCLUSIONS Currently, Credit card risk monitoring system is one of the key tasks for the merchant banks, organization to improve merchants risk management level in an automatic, scientific and adequate way. There are many ways of detection of credit card fraud. If one of these or combination of algorithm is applied into bank credit card fraud detection system, the probability of fraud transactions can be predicted soon after credit card transactions by the banks. And a series of anti-fraud strategies can be adopted to prevent banks from great losses before and reduce risks. This paper gives contribution towards the effective ways of credit card fraudulent detection. Acknowledgments I render my sincere thanks to Dr. Lata Ragha Project(Dean) TERNA Engineering College Nerul,Mumbai for her guidance and encouragement. REFERENCES [1 ] Sandeep Pratap Singh, Shiv Shankar P.Shukla,Nitin Rakesh and Vipin Tyagi "Problem Reduction In Online Payment System Using Hybrid Model" International Journal of Managing Information Technology (IJMIT) Vol.3, No.3, August 2011 [2 ] JERMY QUITTNER."AVOIDING CREDIT CARD FRAUD". =89746andpage=12004 [3 ] Abhinav Srivastava, Amlan Kundu, Shamik Sural and Arun K. Majumdar, "CreditCard Fraud Detection Using Hidden Markov Model" IEEE, Transactions On Dependable And Secure Computing, Vol. 5, No 1., January-March 2008 [4 ] V.Bhusari,S.Patil," Study of Hidden Markov Model in Credit Card Fraudulent Detection ",International Journal of Computer Applications ( ) Volume 20- No.5, April 2011 [5 ] 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 , October 2009 [6 ] Sam Maes, Karl Tuyls, Bram Vanschoenwinkel, Bernard Manderick,"Credit card fraud detection using Bayesian and neural networks,"interactive image-guided neurosurgery, pp , [7 ] Linda Delamaire (UK), Hussein Abdou (UK), John Pointon (UK), Credit card fraud and detection techniques: a review, Banks and Bank Systems, Volume 4, Issue 2, 2009 [8 ] S. Benson Edwin Raj, A. Annie Portia, Analysis on Credit Card Fraud Detection Methods, International Conference on Computer, Communication and Electrical Technology ICCCET2011, 18th & 19th March, 2011 [9 ] Masoumeh Zareapoor, Seeja.K.R, and M.Afshar.Alam, Analysis of Credit Card Fraud Detection Techniques: based on Certain Design Criteria, International Journal of Computer Applications ( ) Volume 52 No.3, August 2012 [10 ] V. Bhusari, and S. Patil, Study of Hidden Markov Model in Credit Card Fraudulent Detection, International Journal of Computer Applications ( ) Volume 20 No.5, April 2011 [11 ] K.RamaKalyani, D.UmaDevi, Fraud Detection of Credit Card Payment System by Genetic Algorithm, International Journal of Scientific & Engineering Research Volume 3, Issue 7, July-2012 [12 ] A. Brabazon, J. Cahill, P. Keenan1, D. Walsh, Identifying Online Credit Card Fraud using Artificial Immune Systems,IEEE Congress on Evolutionary Computation (CEC), 2010 [13 ] Adnan M. Al-Khatib, Electronic Payment Fraud Detection Techniques, World of Computer Science and Information Technology Journal (WCSIT), Vol. 2, No. 4, , 2012 [14 ] Sam Maes, Karl Tuyls, and Bram, Credit Card Fraud Detection using Bayesian & Neural Network, [15 ] Raghavendra Patidar, Lokesh Sharma, Credit Card Fraud Detection Using Neural Network, International Journal of Soft Computing and Engineering (IJSCE)ISSN: , Volume-1, Issue- NCAI2011, June

6 [16 ] Venkata Ganji, Siva Naga Prasad Mannem, Credit card fraud detection using anti-k nearest neighbor algorithm, International Journal on Computer Science and Engineering (IJCSE), Vol. 4 No. 06 June 2012 [17 ] Y. Sahin and E. Duman, Detecting Credit Card Fraud by Decision Trees and Support Vector Machines, International Multiconference of Engineers and computer scientists March, [18 ] Joseph King-Fung Pun, Improving Credit Card Fraud Detection using a Meta-Learning Strategy, Chemical Engineering and Applied Chemistry University of Toronto 2011 [19 ] Vladimir Zaslavsky and Anna Strizhak, CREDIT CARD FRAUD DETECTION USING SELFORGANIZING MAPS, INFORMATION & SECURITY. An International Journal, Vol.18,2006. [20 ] Khyati Chaudhary, Jyoti Yadav, Bhawna Mallick, A review of Fraud Detection Techniques: Credit Card, International Journal of Computer Applications ( ) Volume 45 No.1, May [21 ] Peter J. Bentley,Jungwon Kim,Gil-Ho Jung and Jong-Uk Choi, Fuzzy Darwinian Detection of Credit Card Fraud,2007. [22 ] Ganesh Kumar.Nune, P.Vasanth Sena and T.P.Shekhar, Novel Artificial Neural Networks and Logistic Approach for Detecting Credit Card Deceit, International Journal of Computer Science and Management Research Vol 1 Issue 3 October 2012 [23 ] Abhinav Srivastava, Amlan Kundu, Shamik Sural, Arun K. Majumdar. Credit Card Fraud Detection using Hidden Markov Model. IEEE Transactions on dependable and secure computing,volume 5; (2008) (37-48). [24 ] Bidgoli, B. M., Kashy, D., Kortemeyer, G. & Punch, W. F Predicting student performance: An Application of data mining methods with the educational web-based system LON-CAPA. In Proceedings of ASEE/IEEE frontiers in education conference.. (2003). [25 ] Ekrem Duman, M. Hamdi Ozcelik Detecting credit card fraud by genetic algorithm and scatter search. Elsevier, Expert Systems with Applications, (2011). 38; ( ). [26 ] J. Hunt, J. Timmis, D. Cooke, M. Neal, C. King Development of an artificial immune system for real-world applications. Artificial Immune Systems and their Applications, Springer; (1998). ( ). [27 ] A.J. Graaff A.P. Engelbrecht The Artificial Immune System for Fraud Detection in the Telecommunications Environment ; (2011). [28 ] Nicholas Wong, Pradeep Ray, Greg Stephens & Lundy Lewis (2012). Artificial immune systems for the detection of credit card fraud. Info Systems, Volume 22. AUTHORS First Author is M. E student studying in TERNA ENGINEERING COLLEGE NERUL,MUMBAI. He is having 13 years experience in teaching. Second Author is a M.Tech student studying in VJTI, Mumbai. He is B.E from ADCET. He is having 2 years experience in teaching also he handle various company project. He is member of TGMC. He is also working as a technical advisor for Savari technologies Pvt. Ltd.. He is RHCSE (Redhat certified system engineer) and RHCE (Redhat Certified Engineer). 726