Professional Documents
Culture Documents
Plastic Card Circumvention An in Firmity of Authenticity and Authorization
Plastic Card Circumvention An in Firmity of Authenticity and Authorization
https://www.emerald.com/insight/1359-0790.htm
Plastic card
Plastic card circumvention an circumvention
infirmity of authenticity
and authorization
Vipin Khattri 959
Department of Computer Application, Integral University, Lucknow, India and
Department of Computer Application, Shri Ramswaroop Memorial University,
Barabanki, India
Sandeep Kumar Nayak
Department of Computer Application, Integral University, Lucknow, India, and
Deepak Kumar Singh
Department of Information Technology, Jaipuria Institute of Management,
Lucknow, India
Abstract
Purpose – Currency usage either in the physical or electronic marketplace through chip-based or magnetic
strip-based plastic card becoming the vulnerable point for the handlers. Proper education and awareness can only
thrive when concrete fraud detection techniques are being suggested together with potential mitigation
possibilities. The purpose of this research study is tendering in the same direction with a suitable plan of action in
developing the authentication strength metric to give weightage marks for authentication techniques.
Design/methodology/approach – In this research study, a qualitative in-depth exploration approach is
being adapted for a better description, interpretation, conceptualization for attaining exhaustive insights into
specific notions. A concrete method of observation is being adopted to study various time boxed reports on
plastic card fraud and its possible impacts. Content and narrative analysis are being followed to interpret more
qualitative and less quantitative story about existing fraud detection techniques. Moreover, an authentication
strength metric is being developed on the basis of time, cost and human interactions.
Findings – The archived data narrated in various published research articles represent the local and global
environment and the need for plastic card money. It gives the breathing sense and capabilities in the
marketplace. The authentication strength metric gives a supporting hand for more solidification of the
authentication technique with respect to the time, cost and human ease.
Practical implications – The research study is well controlled and sufficient interpretive. The empirical
representation of authentication technique and fraud detection technique identification and suggestive mitigation
gives this research study an implication view for the imbibing research youths. An application and metric based
pathway of this research study provides a smoother way to tackle futuristic issues and challenges.
Originality/value – This research study represents comprehensive knowledge about the causes of the
notion of plastic card fraud. The authentication strength metric represents the novelty of a research study
which produced on the basis of rigorous documentary and classified research analysis. The creativity of the
research study is rendering the profound and thoughtful reflection of the novel dimension in the same domain.
Keywords Authentication strength metric, Authentication technique, Fraud detection system,
Fraud detection technique, Multifactor authentication, Plastic card fraud
Paper type Literature review
Journal of Financial Crime
Vol. 27 No. 3, 2020
pp. 959-975
The authors give our thank and gratitude towards the Integral University for supporting research © Emerald Publishing Limited
1359-0790
work and providing Manuscript Communication Number-IU/R&D/2019-MCN000664. DOI 10.1108/JFC-03-2020-0034
JFC 1. Introduction
27,3 The plastic card payment is a legacy system for the online payment process (Figure 1). The
evolution of card payment started in 1946, which named as Charge-it, and John Bigins
(Cashco, 2018) created it. After that, many business companies introduced various types of
cards. Currently, financial companies are using Chip and Pin cards for online transactions.
The plastic card implemented because of the ease, need of the users and the safety of the
960 money. The genesis behind the formation of the plastic card payment system was to reduce
the risk in the case of large-scale cash-related security with the banks, merchants and users.
The transaction system requires details of the plastic card (Zareapoor et al., 2012;
Papadopoulos and Brooks, 2011). This ease of use of plastic card also gives opportunities to
the fraudsters for committing plastic card fraud. In the current scenario, fraudsters attack
the sentiment of the human to steal all the information which is required to perform a
fraudulent transaction. In other words, trends of plastic card fraud are changing
dynamically.
In authentication of plastic card transaction, various security features are already
implemented, such as card verification value, personal identification number, 3-D secure
password and chip and pin (Khattri et al., 2020a, 2020b; Sahin and Duman, 2011; Wong et al.,
2012). Despite these security features, the impact of plastic card fraud cannot ignore, and it
is increasing at an alarming rate (Maes et al., 2002; UK Finance, 2019; Arthur Williams, 2007;
Bai and Chen, 2013). In outlook of the impact of plastic card fraud, it has been taken from the
reports of the Australian payment system (Australian Payments Network, 2018; Australian
Payments Network, 2017; Australian Payments Network, 2016; Australian Payments
Network, 2015) and demonstrated statistics using the graph from the year 2010 to till 2017
(Figure 2). It includes four categories of fraud in which are lost/stolen cards, skimming card,
card not present and other card fraud. This graph shows that the loss of the amount is
increasing every year. Especially in the case of card-not-present fraud, it is exceptionally
high. Where the loss of amount in 2010 was $204.5m, it increased to $561.3m in 2017. This
loss means that card fraud has increased about 2.75 times from 2010 to 2017.
For accomplishing the goal of the study, this paper has been divided into five segments.
The second segment renders the prevention techniques, including multifactor
authentication. This segment also explores the relationship of various factors such as time,
cost and human ease on different authentication processes and proposes an authentication
strength metric (ASM). The third segment shows the various detection techniques of plastic
card fraud along with the information of the datasets and evaluation metrics used in the
Figure 1.
Plastic card online
transaction system
fraud detection model. The fourth segment finds the resultant outcome of the study, and the Plastic card
fifth segment depicts the concluding remarks with the future work of the study. circumvention
2. Plastic card fraud prevention techniques
2.1 Authentication
The primary purpose of the authentication process is to allow only legitimate users for
which they are eligible and prohibit those users who are not valid (Khattri and Singh, 2019; 961
Khattri and Singh, 2018a; Dasgupta et al., 2017; Kennedy and Millard, 2016; Gunson et al.,
2011; Barker et al., 2008). At the initial level of security, the most useful authentication
process is the password, and it implements in almost all applications. At the initial level of
protection, the most important authentication process is the password, and it implements in
all applications practically. It applies where security concerns are essential such as banking
and defense sector etc. Apart from this, there are many more authentication processes
among which personal identification number (PIN), one-time password (OTP) and card
swipe use mainly. Different types of authentication processes implement in various
application areas depending on the requirements of an organization’s applications and
security policy. The choice of the following authentication processes depends on some
considerations, such as cost and time participation for the authentication process, the level
of user safety and ease of use of the user and number of users. Different types of
authentication processes can organize into four categories (Figure 3).
2.1.1 The user knows (Type-I). In this type of authentication process, the system wants to
use only that information which is known to the legitimate user. This type of authentication
process uses the password, PIN and secret questions/answers. In this category, the password is
one of the examples which is used mostly everywhere, such as online banking, email access,
online resource access, mobile application and secret document access.
2.1.2 The user has (Type-II). In this authentication process, the system verifies that
object what the user has. The object which has to be verified by the authentication process
must be in charge of the authenticated user. Therefore, that object should be kept safe
because of any ignorance of users; it can be lost or stolen. It can be used by an unauthorized
user to access a legitimate account. ATM card, debit card, credit card, ID card, swipe card,
smart card, cash card, security dongles, etc., are used for verification of legitimate users.
Figure 2.
Yearly loss of amount
using Australian
fraud using the card
JFC
27,3
962
Figure 3.
Authentication types
2.1.3 The user is (Type-III). In this authentication process, the system ensures the actual
presence of humans, which verifies that unauthorized users could not access the legitimate
account. Biometric authentication uses unique human characteristics to prove physical
presence. The unique features of humans include fingerprint, iris, palm, retina, face, voice,
gait, signature dynamics and handwriting dynamics.
2.1.4 The user location (Type-IV). This authentication process uses the user’s location to
authenticate the user as a legitimate user. The user authentication process completes by
using an electronic device that should include the global positioning system (GPS) or IP
address or able to identify the cell tower ID.
The authentication processes are dependent on various factors such as time taken,
the cost involved and the human ease requirement. The mapping of these factors with
all types of authentication process are drawn based on the different levels of security
(Table 1).
From Table 1, the following equations define the relationship of various types of authentication
processes concerning the time, cost and human ease [equations (1) to (5)]:
Time:Cost
Authentication Process Type I / (1)
Human Ease
Time:Cost Plastic card
Authentication Process Type II / (2)
Human Ease circumvention
Time:Cost
Authentication Process Type III / (3)
Human Ease
where wn = w1, w2, w3 and w4 are weights for authentication process types I, II, III and IV,
respectively. The value of these weights ranges from low (0.1), medium (0.5) and high (1).
Figure 4.
Fraud detection
system
Plastic card
circumvention
965
Figure 5.
Artificial neural
network
of legitimate and fraudulent transactions. The review of related work concerning the
detection of plastic card fraud using ANN is being done in the following paragraphs.
The study of Zhang et al. (2018) created a model using a convolution neural network (CNN)
to detect fraud of internet transactions. This model had two components. The first component
was trained for feature sequencing using CNN on historical data. The second component was
used to find a new transaction as legitimate or fraudulent. It was also claimed that the proposed
model achieved 91% precision and 94% recall, and, in comparison with the previous model, it
was found 26% more in precision and 2% more in the recall.
Gomez et al. (2018) proposed a strategy with an artificial neural network to identify
online card fraud. This strategy had divided into two parts. The first part of the strategy
applied consecutive filters for reducing the unbalanced dataset. In the second part, the
neural network classifier implemented to categorized a new transaction as false or genuine.
It claimed that to a certain level, a cascade of filters was a useful and proposed strategy that
showed excellent performance with a real data set.
The study of Fu et al. (2016) proposed a framework for fraud detection using a
convolution neural network based on mining the fraud hidden patterns from the available
dataset. In the first step, the proposed framework performed feature extraction using
aggregation strategies. In the second and third steps, it performed feature transformation
and achieved the result by classifying a new transaction as fraudulent or legitimate. The
study also proposed a trading feature entropy to find the hidden fraud pattern, and the cost-
based sampling was used to handle an imbalanced data set. The final result claimed that the
proposed framework was performed better as compared to the random forest, neural
network and support vector machine.
The empirical study of Sahin and Duman (2011) made a comparative analysis for
analyzing the performance of a fraud detection system of credit card using logistic
regression and artificial neural network on real data sets. The fraud detection system
generated a score against each incoming transaction. Using this score, it categorized the
incoming transaction as a false or genuine transaction. It claimed that the fraud detection
model using an ANN showed superior to logistic regression.
JFC The study of Khan et al. (2014) developed a fraud detection system of the credit card.
27,3 This fraud detection system used a simulated evolutionary algorithm to train the neural
network. It claimed that the accuracy of the system was about 65%.
Figure 6.
Hidden Markov
model
patterns of the cardholder. The study analyzed the spending activities of the cardholder in Plastic card
three different categories: low, medium and high. The study claimed that using HMM, fraud circumvention
detection and removing complexity was very easy. The results of the study found about
87-90% accuracy of the proposed system to detect transactions as fraudulent or legitimate.
Figure 7.
Process of data
mining
JFC sensitive metric. Sahin used ANN and SVM to make comparisons with the proposed
27,3 approach. The final result showed that the performance of the proposed approach
performed best in comparison with the ANN network and SVM.
Mishra and Dash (2014) made a comparative analysis of detection of credit card fraud
with a decision tree, Chebyshev functional link ANN and multilayer perceptron (MLP). The
result found that the multilayer perceptron performed better than the other methods in
968 terms of fraud detection.
Figure 8.
Decision tree
Figure 9.
Evolutionary
algorithm
The study of Assis et al. (2014) proposed a card fraud detection system using genetic Plastic card
programming. The proposed approach performed in three steps: data preparation, genetic circumvention
programming algorithm and data prediction with analysis. It claimed that the performance of
the proposed system increased by up to 17% in comparison to the existing system.
Duman and Ozcelik (2011) developed a method using scatter search and genetic
algorithm for the detection of credit card fraud and applied the existing solution in the
bank to improve the performance. A score was generated against an incoming transaction and
categorized as false or genuine based on this score. The main aim of the study was to reduce 969
false positive and false negative rates. It claimed that after applying the proposed solution,
performance increased up to 200% concerning the existing solution.
An essential element of the fraud detection technique is the data set, which is used for
training and testing the fraud detection system, and valid data sets are not available in the
public domain for security reasons. The other important element of the detection technique
is the evaluation metrics, which are used to find the validation and performance of the
model. From the research perspective, information on data sets and evaluation metrics is
also reviewed and summarized in the table (Table 2). This information will help the
researchers to find the different data sets and evaluation metrics in one place.
4. Discussion
The outcomes of the proposed and reviewed study are explored in terms of four focus areas.
(1) the impact of plastic card fraud on a plastic card transaction;
(2) the impact of multifactor authentication process on proposed ASM;
(3) the challenges of the fraud detection system to detect plastic card fraud; and
(4) the importance of data set and evaluation metrics on the fraud detection system.
Zhang et al. (2018) CNN Real data set of online transaction Accuracy; Precision; Recall; F1
data of a commercial bank B2C score
Gomez et al. (2018) ANN Real data set of card transactions Area of Receiver Operating
Characteristic; Value Detection
Ratio; True False Positive Ratio
Fu et al. (2016) CNN Real data set of credit card of F1 Score
commercial bank
Sahin and Duman ANN; LR Real data set of a nationalized bank of Accuracy; True Positive Rate
(2011) credit card
Khan et al. (2012) HMM Synthetic data set Accuracy
Saia (2017) DWT Transactions of credit card of Area Under the Receiver Operating
European cardholders Characteristic curve; Cosine Table 2.
Similarity; Precision; F-score; Recall
Information of
Sahin et al. (2013) DT Real world data set of credit card Accuracy; True Positive Rate techniques, data set
Mishra and Dash DT; MLP; Data set of UCI machine learning Root mean square error; and evaluation
(2014) ANN repository Accuracy metrics used in the
Assis et al. (2014) GP; EA Real data set of Latin American Accuracy; Sensitivity; validation and
payment system Specificity; Economic Efficiency performance
Duman and Ozcelik GA A real data set from a bank of Existing solution evaluation of fraud
(2011) Turkey detection system
JFC These four areas are an integral part of the fraud prevention and detection system.
27,3 Therefore, researchers have to consider these four areas while building the same.
4.2 The impact of multifactor authentication process on proposed authentication strength metric
In this study, an ASM was proposed to find the strength of the prevention technique, i.e.
authentication technique. At a different level of security, i.e. low (0.1), medium (0.5) and high (1.0),
the ASM was calculated. ASM’s graphs plotted concerning time, cost and human ease. Analysis
of graphs (Figure 11) is showing that the strength of the prevention technique increases as time
and cost increase. However, as human ease increases, then the strength of the prevention
technique decreases. The range of authentication strength (Figure 12) is varied from 0.3 to 30 as
the level of security increases.
4.3 The challenges of a fraud detection system to detect plastic card fraud
On the foundation of the analysis of detection techniques, this study depicts the
challenges of fraud detection systems of plastic card fraud (Sahin and Duman, 2011;
Maes et al., 2002), and these challenges must be considered while developing the fraud
detection system.
50%
37% 40%
40% 35%
26% 27% 29%
30% 23%
20% 14%
10%
0%
–10%
Figure 10.
Country-wise global
plastic card fraud Sources: Kiernan (2017)
Figure 11.
Value of
authentication
strength against time,
cost and human ease
Plastic card
circumvention
971
Figure 12.
Range of
authentication
strength
4.3.1 Imbalanced dataset. The data set of plastic card fraud contains fraudulent transactions
and legitimate transactions also. However, the total percentage of fraudulent transactions is very
less, i.e. 1-2% approximately as compared to the authorized transactions. Therefore, it is a very
tedious task to find the deceptive pattern from a very smaller number of fraudulent transactions.
In other words, finding a needle from the haystack, i.e. distribution of fraudulent transactions is
skewed. Therefore, fraud detection system shows high accuracy with reference to legitimate
transactions.
4.3.2 Error in dataset. When a fraud detection system is trained to classify a
transaction as false or genuine using a fraudulent transaction data set, the performance
of the fraud detection system declines due to an error in the dataset. Because the
performance of the fraud detection system also depends on the quality of the dataset.
These errors can be missing values and errors in stored data. Therefore, before training
the fraud detection system, the data set must be cleaned concerning missing values and
error in stored data.
4.3.3 Similar transaction. In the current scenario, fraudster performs a fraudulent
transaction using a plastic card in a much cleaned way, which seems like a legitimate
transaction. The differentiation between the similar pattern of the fraudulent and
legitimate transaction is almost unable. Therefore, fraud detection system should be
designed in such a way that it could handle the same situation.
4.3.4 Small data set. When training of the fraud detection system is done using a small
data set, then the performance of the system becomes questionable. As a result, accuracy of
the system degrades because the system is not trained with large fraudulent patterns.
Therefore, fraud detection system must be trained with a large data set so that the system
could achieve high accuracy in the detection of the fraudulent transaction using an
exploration of large fraudulent patterns.
4.3.5 Dynamic fraudulent pattern. As the world is moving in the digital era, the digital
transaction is increasing with exponential growth. The patterns of a legitimate and
fraudulent transaction are changing very dynamically. This dynamic nature of fraudulent
transaction decreases the accuracy of the fraud detection system. Therefore, fraud detection
systems must be designed to manage the dynamic nature of fraudsters. It means that the
fraud detection system could update itself dynamically based on the dynamic pattern of the
fraudulent transaction.
4.3.6 False alarm rate. When a fraud detection system identifies a transaction as a
fraudulent transaction but which is not fraudulent in reality, then this situation is known as
a false negative. When a fraud detection system identifies a transaction as a legitimate
JFC transaction that but which is not legitimate in reality, then this situation is known as false
27,3 positive. It means that the fraud detection system wrongly classifies the transaction. As a
result, performance of the system decreases. Therefore, fraud detection system must be
designed to trim down the false alarm rate. The result of a high false alarm rate is the high
loss of money.
972 4.4 The importance of dataset and evaluation metrics on the fraud detection system
The fourth focus area is the data set and evaluation metrics, which are used in the validation
and performance assessment of the system. Due to security reasons, real data sets are not
available openly. In view of the training of the system, data sets play a significant role, this
study has given the information of data sets that are used in the research papers, and any
researchers can use these datasets for testing the system. These data sets are from the UCI
machine learning repository, Kaggle data set, synthetic data set and real data set.
The information on evaluation metrics is also given. These metrics are area under ROC
curve, confusion matrix, detection rate, false positive rate, precision, recall, F1 score,
accuracy, true positive rate, sensitivity, specificity, negative predictive value, economic
efficiency, cost reduction rate, alert rate, Kolmogorov–Smirnov statistics, Jaccard index, key-
value sharing throughput, streaming detection performance, root mean square error, cosine
similarity and misclassification rate. Researchers can use any appropriate metric to assess
and validate the model.
References
Arthur Williams, D. (2007), “Credit card fraud in Trinidad and Tobago”, Journal of Financial Crime,
Vol. 14 No. 3, pp. 340-359.
Assis, C.A.S., Pereira, A.C., Pereira, M.A. and Carrano, E.G. (2014), “A genetic programming approach
for fraud detection in electronic transactions”, in 2014 IEEE Symposium on Computational
Intelligence in Cyber Security (CICS), IEEE, pp. 1-8.
Australian Payments Network (2015), “Australian payments fraud details and data”, available at: Plastic card
www.auspaynet.com.au/sites/default/files/2018-01/Report-australian-payments-fraud-details-and-
data-2015.pdf (accessed 20 April 2019). circumvention
Australian Payments Network (2016), “Australian payments fraud details and data 2016”, available at:
www.auspaynet.com.au/sites/default/files/2018-01/Report-australian_payments_fraud_details_and_
data_2016.pdf (accessed 20 April 2019).
Australian Payments Network (2017), “Australian payments fraud 2017”, available at: www.
auspaynet.com.au/sites/default/files/2018-01/australian_payments_fraud_details_and_data_ 973
2017.pdf (accessed 20 April 2019).
Australian Payments Network (2018), “Australian payment card fraud 2018”, available at: www.
auspaynet.com.au/sites/default/files/2018-08/AustralianPaymentCardFraud-2018-Report.pdf
(accessed 20 April 2019).
Avghad, S.D. and Joshi, M.S. (2015), “Securing online banking transaction using predictive
approach of hidden Markov model”, International Journal of Computer Applications, Vol. 128
No. 7, pp. 14-17.
Bai, F. and Chen, X. (2013), “Analysis on the new types and countermeasures of credit card fraud in
mainland China”, Journal of Financial Crime, Vol. 20 No. 3, pp. 267-271.
Barker, K.J., D’Amato, J. and Sheridon, P. (2008), “Credit card fraud: awareness and prevention”, Journal
of Financial Crime, Vol. 15 No. 4, pp. 398-410.
Bhusari, V. and Patil, S. (2011), “Study of hidden Markov model in credit card fraudulent detection”,
International Journal of Computer Applications, Vol. 20 No. 5, pp. 33-36.
Carneiro, N., Figueira, G. and Costa, M. (2017), “A data mining based system for credit-card fraud
detection in e-tail”, Decision Support Systems, Vol. 95, pp. 91-101.
Cashco (2018), “The history of plastic money”, available at: https://cashcofinancial.com/2016/01/the-
history-of-plastic-money/ (accessed 3 April 2019).
Dasgupta, D., Roy, A. and Nag, A. (2017), “Multi-factor authentication”, Advances in User
Authentication. Infosys Science Foundation Series, Springer, Cham, pp. 185-233.
Duman, E. and Ozcelik, M.H. (2011), “Detecting credit card fraud by genetic algorithm and scatter
search”, Expert Systems with Applications, Vol. 38 No. 10, pp. 13057-13063.
Fu, K., Cheng, D., Tu, Y. and Zhang, L. (2016), “Credit card fraud detection using convolutional neural
networks”, International Conference on Neural Information Processing, Springer, Cham,
pp. 483-490.
Gomez, J.A., Arévalo, J., Paredes, R. and Nin, J. (2018), “End-to-end neural network architecture for
fraud scoring in card payments”, Pattern Recognition Letters, Vol. 105, pp. 175-181.
Gunson, N., Marshall, D., Morton, H. and Jack, M. (2011), “User perceptions of security and usability of
single-factor and two-factor authentication in automated telephone banking”, Computers and
Security, Vol. 30 No. 4, pp. 208-220.
Kennedy, E. and Millard, C. (2016), “Data security and multi-factor authentication: analysis of
requirements under EU law and in selected EU member states”, Computer Law and Security
Review, Vol. 32 No. 1, pp. 91-110.
Khan, A.U.S., Akhtar, N. and Qureshi, M.N. (2014), “Real-time credit-card fraud detection using
artificial neural network tuned by simulated annealing algorithm”, in Conference on Recent
Trends in Information, Telecommunication and Computing, ITC, pp. 113-121.
Khan, A., Singh, T. and Sinhal, A. (2012), “Implement credit card fraudulent detection system using
observation probabilistic in hidden Markov model”, in 2012 Nirma University International
Conference on Engineering (NUiCONE), IEEE, pp. 1-6.
Khattri, V. and Singh, D.K. (2018a), “A novel distance authentication mechanism to prevent the
online transaction fraud”, in Advances in Fire and Process Safety, ô Springer, Singapore,
pp. 157-169.
JFC Khattri, V. and Singh, D.K. (2018b), “Parameters of automated fraud detection techniques during online
transactions”, Journal of Financial Crime, Vol. 25 No. 3, pp. 702-720.
27,3
Khattri, V. and Singh, D.K. (2019), “Implementation of an additional factor for secure authentication in
online transactions”, Journal of Organizational Computing and Electronic Commerce, Vol. 29
No. 4, pp. 258-273.
Khattri, V., Nayak, S.K. and Singh, D.K. (2020a), “Development of integrated distance authentication
and fingerprint authorization mechanism to reduce fraudulent online transaction”, Intelligent
974 Communication, Control and Devices, Springer, Singapore, pp. 73-83.
Khattri, V., Nayak, S.K. and Singh, D.K. (2020b), “An enhanced authentication technique to mitigate the
online transaction fraud”, Intelligent Communication, Control and Devices, Springer, Singapore,
pp. 123-132.
Kiernan, J.S. (2017), “Credit card and debit card fraud statistics”, available at: https://wallethub.com/
edu/credit-debit-card-fraud-statistics/25725/ (accessed 15 October 2019).
Maes, S., Tuyls, K., Vanschoenwinkel, B. and Manderick, B. (2002), “Credit card fraud detection using
Bayesian and neural networks”, in Proceedings of The 1st International Naiso Congress on
Neuro Fuzzy Technologies, pp. 261-270.
Mishra, M.K. and Dash, R. (2014), “A comparative study of chebyshev functional link artificial neural
network, multi-layer perceptron and decision tree for credit card fraud detection”, in 2014
International Conference on Information Technology, IEEE, pp. 228-233.
Nabha, K., Neha, P., Shraddha, K., Suja, S. and Amol, P. (2015), “Credit card fraud detection system
using hidden Markov model and adaptive communal detection”, International Journal of
Computer Science and Information Technologies, Vol. 6 No. 2, pp. 1795-1797.
Ngai, E.W., Hu, Y., Wong, Y.H., Chen, Y. and Sun, X. (2011), “The application of data mining techniques
in financial fraud detection: a classification framework and an academic review of literature”,
Decision Support Systems, Vol. 50 No. 3, pp. 559-569.
Ogwueleka, F.N. (2011), “Data mining application in credit card fraud detection system”, Journal of
Engineering Science and Technology, Vol. 6 No. 3, pp. 311-322.
Papadopoulos, A. and Brooks, G. (2011), “The investigation of credit card fraud in Cyprus: reviewing
police effectiveness”, Journal of Financial Crime, Vol. 18 No. 3, pp. 222-234.
Patidar, R. and Sharma, L. (2011), “Credit card fraud detection using neural network”, International
Journal of Soft Computing and Engineering, Vol. 1, pp. 32-38.
Prakash, A. and Chandrasekar, C. (2015), “An optimized multiple semi-hidden Markov model for
credit card fraud detection”, Indian Journal of Science and Technology, Vol. 8 No. 2,
pp. 165-171.
RamaKalyani, K. and UmaDevi, D. (2012), “Fraud detection of credit card payment system by
genetic algorithm”, International Journal of Scientific and Engineering Research, Vol. 3 No. 7,
pp. 1-6.
Sahin, Y. and Duman, E. (2011), “Detecting credit card fraud by ANN and logistic regression”, in
International Symposium on Innovations in Intelligent Systems and Applications, IEEE, pp. 315-319.
Sahin, Y., Bulkan, S. and Duman, E. (2013), “A cost-sensitive decision tree approach for fraud
detection”, Expert Systems with Applications, Vol. 40 No. 15, pp. 5916-5923.
Saia, R. (2017), “A discrete wavelet transform approach to fraud detection”, in International Conference
on Network and System Security, Springer, Cham, pp. 464-474.
UK Finance (2019), “Fraud the facts 2019”, available at: www.ukfinance.org.uk/system/files/
Fraud%20The%20Facts%202019%20-%20FINAL%20ONLINE.pdf (accessed 10 April
2019).
Wong, N., Ray, P., Stephens, G. and Lewis, L. (2012), “Artificial immune systems for the detection of
credit card fraud: an architecture, prototype and preliminary results”, Information Systems
Journal, Vol. 22 No. 1, pp. 53-76.
Zareapoor, M., Seeja, K.R. and Alam, M.A. (2012), “Analysis of credit card fraud detection techniques: Plastic card
based on certain design criteria”, International Journal of Computer Applications, Vol. 52 No. 3,
pp. 35-42. circumvention
Zhang, Z., Zhou, X., Zhang, X., Wang, L. and Wang, P. (2018), “A model based on convolutional neural
network for online transaction fraud detection”, Security and Communication Networks,
Vol. 2018, pp. 1-9.
Corresponding author
Sandeep Kumar Nayak can be contacted at: nayak.kr.sandeep@gmail.com
For instructions on how to order reprints of this article, please visit our website:
www.emeraldgrouppublishing.com/licensing/reprints.htm
Or contact us for further details: permissions@emeraldinsight.com