Credit Card Fraud Identification: A Complete Review

This research aims to review and examine different algorithms for credit card fraud detection. The study analyzes various techniques and methods used for fraud detection and identifies the best algorithm for decreasing credit card frauds. The research concludes that the Random Forest algorithm is the most effective solution for detecting credit card frauds.

University
*** Semester
Credit Card Fraud Identification
complete Review: Past and Present
Student Name:
Register Number:
Submission Date:

Credit Card Fraud Identification, a complete Review: Past and Present
Abstract
997458
The conducted research work aims on reviewing and examining thirty journals of different
publication to understand the system which detects the credit card fraud. This research's main
purpose refers idenitfying the system's frauds and to search for the best algorithm which
decreases the credit card frauds. This is regarded as a challenging task, because of the existance
of many tools, techniques or methods for the fraud detection. For each data transaction fraud
detection, distinct algorithms are utilized, for example the clustering methods, machine learning
algorithms and so on. The completion of this analysis determines that the Random forest
algorithm is the nest algorithm or the solution which could detect the credit card frauds. This
specific algorithm is selected from the review of 30 journals, which meets parameters of cost
effectiveness and system efficiency. It is extremely important to implement an algorithm which is
powerful enough, as the algorithms are the main component which detects the credit card frauds.
Moreover, it ensures to decline the number of frauds and decreases the harms of theft and frauds.
Thus, several algorithms and methods have been reviewed, followed by visualization, system
classification, system evaluation and system validation. The system classification process
concentrates on the data such as device number, Data Type, field of study, fraud detection
technique etc. Then, the system evaluation is conducted depending on the factors such as data
collection from a transaction set, the algorithms for fraud detection, analyzing of data, data
storing, data classification based on a behavioral pattern, control layers, decision making fora
transaction with respect to fraud, and proving customer notification. It is determined that the
utilization of productive and result oriented algorithms and procedures, one can meet the
objectives which have zero tolerance for the credit card frauds. The statistics and application of
algorithms are used for detecting the credit card frauds for both online and off line transactions
of the end users.
Keywords: Supervised & Unsupervised Models, Credit card cheating, Shams, Algorithms,
Identify Fraud, Data Mining.
1

1. Introduction
In today's modern world of advanced technology, it is vital to be aware of affects related to fraud
and theft. Specially related to financial and money related frauds. Lot of research work is being
conducted and Technology invented to reduce the amount of frauds associated with credit cards.
The main concern of banks, companies, firms, individuals, end user is credit card theft and how
this can be prevented all together. These theft and frauds can be of different types. We shall
discuss and try to understand this issue and the problem faced by the industry.
Normal framework, system servers and networks are vulnerable to outside potential threats and
security attacks. This can be due to unreliable and not maintained infrastructure, no anti-virus
precautions, no reliable malwares, low security, and data compromise. Understanding the past
history and past cases, records related to frauds and thefts, we can predict and can become
proactive against any possible attack on the credit card data. By analysing the past data we can
understand behaviorof fraudster’s and hackers. A wide spectrum of data classification and
discipline is required to maintain a proper anti-theft policy and strong safety features. The role of
the system administrator and supervisor becomes vital and important for maintaining the
standard of system/ Networkswhich are related to credit card data and information.
Classify the event as a fraud and a threat, we shall make use of the supervise model to make
absolute certain and for classification of that event which was studied by Bolton and Hand in
2002. Few measures are provided for identifying and for classifying the events. Events which are
abnormal, uncommon can be detected by the supervised methods and procedures. To detect the
various types of frauds, a fraud model can be utilized. As per the symptoms of an event which is
related historical fraudulent cases, the abnormality is classified. Further investigation should be
done on such cases and this will not prove that these current events are suspicious and
fraudulent. This is just a start for more data gathering, information, collection of evidence and
further investigation study to determine the truth of the case. (Nisbet, Miner, Yale, Elder &
Peterson, 2018; Kültür, Y., & Çağlayan, M. U., 2017; Bahnsen et al., 2017; Zhao et al.,
2016).Active learning strategies can be beneficial for fraud detection (Carcillo, F., 2018).
Online shopping has become the new craze in today’s world with rapid increase and penetration
2

of internet in the whole world. There is a demand for e-commerce and thus this leads to multi
users on the web doing many transactions by using their cards, net banking, credit cards, e-
wallets etc. The most used out of these all transaction modes is the Credit card. More the credit
card is used on e-commerce platforms, the more the chances of theft and stolen data. These all
ultimately leads to financial thefts and losses. Now the authors of these papers have come up
with an innovative method to detect such frauds. Understanding and analysing the behavioral
patterns and transaction data of the credit card user is taken and processed into an algorithm to
get a certain pattern of behavior. This specific type of data of the cardholder is then used to
identify the online fraud when it detects a new fraud. This new thought of conceptual drift is
used as a feedback mechanism for detecting the process and ultimately solving the fraud.
(Jiang, Song, Liu, Zheng & Luan, 2018).
The ultimate aim of this project and study is to come up with the best algorithm that will detect
the frauds in credit card and the various types of theft/ frauds that can occur and how to detect
them. They have been able to identify a few proven methods for solving this enigma. Data
mining, Machine learning, Forward-Backward Greedy algorithm, Artificial Neural Network,
Decision Tree etc are some of the technics and procedures that will be considered.
Understanding the process of evaluating and picking up the right method in the
detection of credit card fraud by validating the process and considering various tested methods
based on research paper analysis based on the outlined data information, Techniques and
components. Pinpointing and identifying the future developments based on the past historical
data and comparing it with present collected data.
Evaluation, study and analysis will be carried out for identifying the credit card hacks, thefts and
frauds on different platforms and networks with the aid of custom made algorithms. Assistance
of the two types of classification that was defined before i.e. Supervised and Unsupervised
Systems will be taken to identify the perfect direction in pinpointing these frauds on any of the
platforms and networks being used.
Lot of hard work and efforts have been put in by these authors to solve and come up with an
answer for this issue and how to overcome and benefit by using their researched technic. The
3

parameters that we shall use when using these technics will be simply be the accuracy,
effectiveness, and cost.
Now, the process will include the following steps,
Firstly we shall determine the process of detecting and identifying a fraud. There will be a
discussion on this matter and the best possible method will be selected.
Second step will be to review and study research papers which have identified previous cases
and how they were used for thefts and frauds.
Third, we shall come up with the technics and the methods to deal with the frauds. Selection of
the best possible technic is analyzed and chosen out of the lot. Subjecting the system to various
tests and identifying the areas also will be taken into consideration. The best 12 algorithms will
be selected and reviewed as to how they will be used and how they will prevent future frauds in
the system.
The Best working Algorithm out of the 12 algorithms shall be taken for identifying the credit
card frauds and thefts and which will be part of the final stage of our project.
With the ever increasing population of online users and the numerous transactions that take place
online by individuals using their credit cards, it becomes more than ever to understand and make
a formal classification for frauds and thefts related to credit cards. Development of various fraud
detection methods and procedures are being developed and researched by various groups with
use of individual data and information, evaluating the same and their credit card usage history.
(Jiang, Song, Liu, Zheng &Luan, 2018; Jiang et al., 2018; Bahnsen et al., 2016; Ganji &
Mannem, 2016).
2. Literature Review
We shall now understand and share our views on the various algorithms and different types of
procedures and technics in Credit card fraud identification. The 12 chosen algorithms as per
previous discussion will be considered and analyzed as to how best they can be used against the
credit card frauds.
4

2.1 Fraud-BNC Algorithm
A specific Bayesian Network Classifier (BNC) algorithm based on the principle ofFraud-
BNCmethod and was designed by de Sá, A. G., Pereira, A. C., & Pappa, G. L. (2018) which shall
use data and information from all the credit card frauds, history and data in the real world issues.
The idea behind this is to better the data classification for identifying thedeceit and malpractice.
The usage and support of the Bayesian algorithm which is customized is taken. The main
problem with this method is that the Data categorization was not used and implemented properly
for identifying the frauds and thefts. Applying and using this for Data classification and
unbalanced data and by using the fraud detection techniqueswhich again are used with the help
of customized BNC algorithm, economic metrics’ efficiency, classification of metrics and
elements of the Fraud detection algorithm can solve this issue. To help this classification of
imbalanced data we shall use the better featuresof the given system. This shall decrease 72
percent of fraud tractions once it is implemented in the system. This method will be used to
identifying the Fraud detection and problems which can lead to financial damages to the
company. The system will keep the information of all the deals and transactions that includes the
end users, companies and organizations. (Bahnsen et al., 2016; Save et al., 2017).Transaction’s
authorization is granted only if the permittedthreshold value is passed or else there will be no
Transaction(de Sá, Pereira & Pappa, 2018).
2.2 Random Forest Algorithm
The root cause of Card frauds is because of all the information that is declared by the user which
includes the card name and personal information. This leads to hacks and card frauds from the
system. (Niveditha, G., Abarna, K., & Akshaya, G. (2019). By correctly identifying, checking
and having a control on these will minimize these issues. A trained and programmed model based
on standard attributes is used for monitoring the transactions by users and the behavior and
actions of this user is tested by this model. If this model senses some irregularity as per its
parameter than it will reject the transaction. Synthetic Minority Over-sampling Technique or
“SMOTE” can be used for this purpose and which is based on a statistical method. (Fiore et al.,
2017; Jurgovsky et al., 2018; Dal et al., 2018). Development of multiple trees and integrating all
these data and information on the entire tree gives good results, whose base is based on the
5

random tree principle. Thus this gives very good and accurate results i.e., about 98.6
percent(Niveditha, Abarna & Akshaya, 2019).
2.3 Machine Learning Algorithms
A lot of scholarly papers and research analysis have encouraged the use of machine
learning algorithm (Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P., He-
Guelton, L., & Cael). There is an increasing substantial challenge for the financial organizations
and for the service providers as there is increase in online transactions by users in way of
electronic payments and by ec0mmerce portals and platforms. (Fan, Han & Liu, 2017; Fahmi,
Hamdy & Nagati,2016; Duchi, Hazan & Singer, 2011; Fercoq, & Richtárik, 2018). A slow and
somewhat time lag procedure which is caused due to the slowly creeping in of the above method
way into the business applications because of its demand and accuracy but which overall results
into detection of the various theft and frauds.The speed to detectthe frauds on o ine transactionsffl
has to be increased as per the rapid increase in technology and online users. For the offline
transaction frauds, machine learning has proved to be more effective and penetrative with the
help of the method as discussed. Long Short-Term Memory (LSTM) is one such method that is
used for this process and it has proved to have a very good detection capability. (Jurgovsky et al.,
2018; Aleskerov, Freisleben & Rao, 2016).
2.4 ANN
Information from the day-to-day transaction will be used in the identification and understating
the characteristic features of a normal or fraudulent transaction and this is also taken in the
reporting and data from the historical transactions cases. (Choi, D., & Lee, K. 2018; Zareapoor &
Shamsolmoali, 2015).In present world, more importance is to incorporate an effective system to
detect the credit card defects and frauds as it is a common thing and the usage is rampant and
very frequent. (M. Simi. (2009)). Random Forest, ANN (Artificial Neural Network) and SVM
(Support Vector Machine) are some of the most common machine learning supervised technics
and algorithms aids in detecting and determining this detection of online credit frauds and hacks.
It has very good detection and accuracy level when compared to the other algorithms such as
ANN and SVM (Rajeshwari & Babu, 2017; M, 2009; Gómez et al., 2018;Carcillo et al.,2018).
6

2.5 Data Mining Algorithms
There can be lot of complications and confusions in large transactions and its related
frauds.(Zanin, M., Romance, M., Moral, S., & Criado, R. (2018). Here the importance of data
mining algorithms comes into picture. This problem of absence of metrics synthesizing to initiate
the global structure for data mining algorithms can be removed by the advanced system proposal,
which uses the proper and accurate integration of network metrics. There is a marked
improvement in the classification.Banks are the most beneficial from this technique which
arranges and manages the complicated organizational projects.16% to 12% drop in error rate
proves its power and detection success. For the overall success and improvement of data
detection frauds, combined use of neural network and data mining should be considered and
utilized. Special mention should be made of the super and more reliable method in use of neural
network for its high accuracy and detection in credit card cases. (Fu et al., 2017; Zanin et al.,
2018; Yee, Sagadevan & Malim, 2018).
2.6 Anti-k nearest Neighbor Algorithm
CardCom is the one utilized todetect the fraud as per the research paper (Robinson, W.
N., & Aria, A. (2018)). The card’s sequence, unique approach with numbering method is used for
the fraud detection in various organizations. If the data usage and the data is modified than the
validate transaction, recall and result all will change and be different. Raw and unused Data plays
a very important role in detection resultsand also for sorting and evaluating these raw data
The machine learning and classifiers’ implementation will reduce the drawbacks’ in CardCom’s
limitations.( Bahnsen et al., 2016; Ganji & Mannem, 2016).
2.7 Decision Tree Algorithm
Various opportunities come along for detecting credit card frauds and thefts as perCarta,
S., Fenu, G., Recupero, D. R., & Saia, R. (2019). This paper gives their view point that there will
be viruses, bugs and Credit card thefts and frauds even if the system and the network has all the
malwares, anti-virus software’s and programs. (Vaughan, G., 2018). Use of the (Prudential
Multiple Consensus) PMC model is taken to apply this research paper to the e-commerce
business. With the ever increasing presence of individuals on the net and thus a direct increase in
the transactions over e-commerce trades and buying will lead to more credit card related issues
7

and problems. The abnormalities, loopholes and vulnerable areas have to be identified and
analyzed with the help and the ANN integration to the system and from the transaction set.
(Zhang, J., 2019; Zhou, H., Chai, H. F., & Qiu, M. L. 2018). With the future modified system,
appropriate decisions could be taken (Carta, et al., 2019; Fan, Han & Liu, 2017; Tang,et al.,
2019; Fercoq, & Richtárik, 2018).
2.8 ID3 Algorithm
According to Tang, X. B., Liu, G. C., Yang, J., & Wei, W. (2018),the fraud detection
system was invented depending on the financial statement frauds. As the increase in the online
frauds in credit usage and e-commerce deals increases, there should be an understanding in
providing the financial statements for improving the overall safety of the system. Detection of
the frauds will be directly benefited by timely detection if these are linked to the frauds and
thefts. Financial statement given by banks at every user’s request and notice have to be analyzed
and studied for making the best use of these data and by evaluating, analyzing, reviewing, the
transaction statements. Usage and help of the Machin learning will prove a big helpful hand to
detect this type of financial data/attributes. (Tang,et al., 2019; McGuinness & Frank van
Harmelen.,2018; Noy et al., 2018).
2.9 Clustering Algorithm
A Red flag methodis one of the various approaches used for card detection frauds.
(Baader, G., & Krcmar, H., 2018; Duchi, Hazan & Singer, 2011). Use of the clustering
algorithmwill aid in helping to decrease this irregularities of the raw and classified data and also
including the sorted out data.(Wang, C., & Han, D. (2018), This method will effectively
categorize the raw data and with the help of the k means algorithm which can be used for this
purpose. This paper shall discuss about the clustering of the data and how the vector model
proves to be a separate and unique method for the identification of this fraud system. This will be
separate than the model which is implemented and being used for the early detection of the
thefts. (Rajeshwari & Babu, 2017; Carcillo et al,2018; Wang, C., & Han, D., 2018; Fiore, U., De
Santis, A., Perla, F., Zanetti, P., & Palmieri, F., 2017).
8

2.10 Forward–Backward Greedy Algorithm
Detecting the fraud cases and theft incidents against the credit cards will be an
experiment that was conducted while detecting the anomaly (Hou, D., Cong, Y., Sun, G., Liu, J.,
& Xu, X. (2019). For this experiment, the binary data sets were used and the same will be sued
to conduct the experiment on the binary data sets. There were some Outliers who were
conducting and with thought that the values will be positive while the other normal values will
be considered to be of negative values (Hou et al., 2019).
2.11 Gradient Descent Algorithm
All the attacks, thefts, viral/malware issues and credit card frauds which are the main problems
in the system along with the other problems faced like logistic regressions, shallow neural
networks, and decision tree, which are also the issues faced by the authorities in dealing with the
credit card usage (Kim, E., Lee, J., Shin, H., Yang, H., Cho, S., & Nam, S. et al. (2019)). We
shall be using the FDS systems for the applications in this case study. Data models will be
utilized in detecting and questioning about the data of the users which will also focus on the real
data available to the system and part of these findings. These shall be used in the model as
explained by the authors in this case. Not even a single assigned data could pass without
applying it to each of the models (The Washington Post,2016; Kim, 2019).
2.12 Meta-Heuristic Algorithms
The System’s cost sensitive forms a major part of this study and its primary feature. According to
Nami, S., & Shajari, M. (2018), cost effective nature in usage of the Bayesian network and that is
used in many different models won’t be like other models and technics. These will deliver the
right technology and the system for detecting the frauds and the thefts in the system and which
can be said to be important and effective. The said system contains the capacity of fraud
detection and the cost will not be the factor as it will be within the limits. This was proved by this
research work and analysis. Thus research can be done on the neural network
and the system application as cost effective method which is again part of this research work.
(Nami & Shajari,2018).
9

2.13 Best Solution
So, the Random Forest algorithm is determined as the best answer to all the research and
scholarly papers that we have gone through and the various methods that we have studied. It is
best algorithm and which satisfies all the criterias and parameters.(Niveditha, G., Abarna, K., &
Akshaya, G. (2019)). This shall be integratedto the main system and will be able to get accurate
and stable predictions by the use of the random forest algorithms. This shall develop a multiple
trees which will form the part of the decision trees. The accuracy of this is 98.6 percent which is
very good considering the cost effective method and which has both the categoricaland
numericalfeatures (Nami & Shajari, 2018; Niveditha, Abarna & Akshaya, 2019; Robinson &
Aria, 2018; Van Vlasselaer et al., 2017).
\
Figure: Exact figures for original and fake credit cards (Niveditha, Abarna & Akshaya, 2019).
3. System Components
Various data which has been taken and identified for cost effectiveness, the accuracy, the
efficiency and for credit card fraud detection review being hold up. Many people have been
conducting research and exploring the possible ideas for these answers. There were lot of
research papers and several articles written by the above mentioned researchers for the solution
but were not accepted as they did not know the right approach for this issue. In spite of writing
good articles and methodology they were not accepted by the authorities. We shall now see the
right and correct method of approach for these and use of real-time applications will be
10

considered.
We shall have the discussion and the analysis of usage of Credit card and how it is
critically benefit and includes some computational constraints imposed by the computer systems
and networks on which the data is passed. To understand the logic and for evaluating the
methods, we shall consider the below given factors and parameters while coming up with the
methodology,
1) Which were the types of algorithms which were used?
2) The Detection of the fraud will be how?
3) Once the fraud has occurred, how will the organization/ user know about it?
4) Is the method cost effective and have an accurate result?
The factors that were considered for the grouping and categorizing, analyzing the fraud
identification of credit cards in a system includes the following – Data collection from a set of
transaction, Processing algorithm or Fraud detection algorithms, analyzing the data, Data storing,
data classification based on the behavioral patterns, decision making for the transaction based on
fraud, Layers of control, and providing customer notifications (Fiore et al., 2017; Jurgovsky et
al., 2018).
Thus, we will consider the below parameters in analyzing the above parameters as given,
1) Transaction set and the collection of data for it.
2) Benchmark of data
3) Real world data
4) Second stage the cost sensitive detection
5) Experimental setup
6) Efficiency of the economic metrics.
7) For the fraud from the transaction, the Decision making system.
8) Maintaining cost sensitive matrices.
9) Final decision
10) Initial stage for the first fraud detection.
11) Neural network
12) Deep Artificial neural network
13) Individual models for detecting the credit card frauds.
11

14) Machine learning application
15) Data sampling
16) Real-time fraud detection module
17) Feature selection
18) Data collection with the help of transactions.
19) Analysis and storage of Data.
20) Giving customer notifications.
Table 1: System Components
12

3.1 Visually Processed Data
The Data related to the visual processing isobtained as the visualization processing completes,
which the end user views at the end.Visualization processing is divided into a set of three sub-
classes such as Analyzed imaging data, derived data and priorknowledge data. The main
attributes of the analyzed imaging data is to outline the data primitivesmade up ofinstances such
as contour, point and surface. By analysing the credit card holder’s history and prior
understanding of the knowledge of data, usage reports, information which is unreliable, certain
13

pattern in the users history, attributes, etc.
The sub-class, attributes, and instances with the component data is displayed in table No.1 and
the figure for the same is given below,
Figure: Credit card fraud detection
3.2 Visualization
The use of Visualization Technique is applied for the successful processing and to change various
data that are retrieved to achieve the best pictorial representation, as and when needed. For data
visualization, there are several techniques or algorithms that are used to maximize the accuracy
and the performance, which is represented in the Table 2. The relating graph is displayed in the
below figure. The reason to use the visualization processing includes the creation and changing
the diverse obtained data for accomplishing the best pictorial portrayal for that progression at a
required time. For data visualization, several techniques or algorithms are used to maximize the
fraud detection’s performance and accuracy. In a credit card fraud detection process, the
operational, anatomical, and strategical data could be imagined by suing several algorithms that
upgrades the view. The restriction in the visualization procedure chiefly incorporates anatomical
data.
14

The time and efforts needed for reviewing the daily data order can be decreased with the use of
visualization. It is a graphical diagram, which could be connected to an email and message
service where, the user gets alerts due to the detection of suspicious activity.
Figure: Visualization Process
4. System Classification
The current work’s scenario and its overview in a domain which we wish to work is given in this
particular section named, System classification. It is developed in order to forgive an overview
for the same. The most recent publication is selected who have the research group and the
authors of that group. Utilizing distinct algorithms which are selected based on the research
papers of credit card fraud detection, when the publishers haven’t mentioned the same in their
related research study. Table 2, provides complete information of all the 30 publications and
papers, where the columns represent the components.
The need of this research and analysis is Q1 and Q2, which are ranked for a limited and precise
research data ranging from 2016 to 2018. It ensures to collect additional data or information to
increase the clarity of the current system and the domains. The main focus of these research
papers and research material reflects on malicious activities, thefts, and frauds in credit card
transactions.
Research papers were also included from the following sectors of mixing augmented and virtual
data, color correction,image processing, and processes utilized in the training purpose, and for
15
Visualization
Algorithm
Smart phone, laptop and PC
Data storing
Transparency
Transaction blocking rule
Fraud detection

understanding a vaster field of knowledge and information. The chosen solutions and answers
from all the research papers are included and their sub class and sub sectors with all the
information is selected and displayed in the table format as given,
Based on all the parameters, 30 journals were reviewed, from which 12 best solutions are
described in the below mentioned Table 2for classification of components. Each feature of the
proposedtaxonomy will be reviewed and discussedto summarize the provided solutions.Each
component is depicted as column in the below table.
Table 2:System Classification Table
16

17

18

19

20

N/S: Not specified
5. System Evaluation and Validation
It is essential for the Credit card fraud detection study for locating and identifying the
components and parameters that are relevant to this research study. They can be used as an
additional factor to improve the detection methodology and the system’ overall performance.
This project represents the significance of the utilized parameters i.e., the evaluation and
validation. The evaluation factor is used for concentration on the benefits and the extra
advantages to the complete system. The validation components assist to add on accuracy and to
build a perfect system, which could be built with the help of project’s refined parameters.
The following section will show how these components of validated and evaluated result are
used in the selected publications as per Table no.3 which is displayed below,
Table 3: Evaluation and Validation algorithms with its components
21

22

23

24

25

26

The systems as mentioned have a common factor of validation or evaluation criteria described in
their papers.
27

28

29

30

31

32

33

6. Result and Discussion
The below section, from the publications evaluates and reviews the system components.
The existence and lack of these components are reviewed. Totally, thirty publications are
considered for the components for the detection of credit card fraud, whose components are
compared. The below section presents a comparison of all the components and will outline its
significance. At last, it discusses the chances of improvement.
6.1 Data
This section talks about most of the publications which considers data and how the data is
classified. In this review, it is observed that the raw data is classified into Behavioral patterns,
credit card fraud, concept drift, XGBoost Fraud detection, Bankcard enrollment, GBDT, Mobile
payment, Fraud detection, Mobile device based, patterns, Process mining, Red flags, and so on.
It is hard to decide the use of the retrieved data from the publication papers, as the classification
considers various factors like accuracy, cost effectiveness and efficiency in the technique which
detects the credit card frauds. The above specified factors need additional time and are tiring to
be covered. It is observed that the experimental data in all the publications used the real time
transaction data (transaction history). The publication’s experimental data ensures in data
validation and evaluation. The rest of the publications utilize data classification to detect the
frauds by using customized Bayesian algorithm (de Sá, Pereira & Pappa, 2018).
Credit card fraud detection is categorized into a couple of techniques such as classifier
based detection and anomaly detection(Jiang, Song, Liu, Zheng, & Luan, 2018). The overview of
the device type is mentioned, but the device number is not mentioned by all the publications. The
34

use of applications and mobile devicesare specified,however the brand or any use of OS is not
specified by Hou, D., Cong, Y., Sun, G., Liu, J., & Xu, X., (2019). Chinese bank card enrolment
data set is used by Zhou, H., Chai, H. F., & Qiu, M. L.,(2018), whereas detection of fraudfor a
large data set in a ERP system is used by Baader, G., & Krcmar, H., (2018). On the other hand,
Nami, S., & Shajari, M. (2018) uses Fraud data,Transaction with fraud payment cards,
Transaction with authorized payment cards and all transactions. Zanin, M., Romance, M., Moral,
S., & Criado, R. (2018) just uses the Transaction on credit card data.It is difficult to consider all
the data, due to its huge number of varieties. Only the selected variables are analyzed and thus
extracts the system components and sub-components. Finally, it is concluded that all the
publications don’t actually need to utilize same components, and they could produce their own
factors. From this evaluation, it is believed that if all the publications considerall the data
variancesthen might not be beneficial, as it may not be that essential in the author’s utilized field.
But, it is believed that the utilization of clear data which contains exact input size and real time
data, the definite specification is essential to gain efficiency.
Moreover, it is important to have clear data, exact data size and respective efficiency
specification.
6.2 Credit Card Fraud Detection Techniques
To detect the credit card frauds various publications utilize distinct techniques like
Robinson, W. N., & Aria, A. (2018) utilizes store-centric method, then Carta, S., Fenu, G.,
Recupero, D. R., & Saia, R. (2019) utilizes Information Security, moving further Tang, X. B.,
Liu, G. C., Yang, J., & Wei, W. (2018) uses the credit card fraud detection, next Choi, D., & Lee,
K. (2018) utilizes Fraud Detection, then Hou, D., Cong, Y., Sun, G., Liu, J., & Xu, X. (2019)
utilizes Anomaly Detection technique, and Fiore, U., De Santis, A., Perla, F., Zanetti, P., &
Palmieri, F. (2017) utilizes the Machine Learning algorithm. Same techniques are observed from
the reviewed publications are Credit card detection and fraud detection as utilized by Kim, E.,
Lee, J., Shin, H., Yang, H., Cho, S., & Nam, S. et al. (2019) and Nami, S., & Shajari, M. (2018).
They contain same factors for all most all the publications such as accuracy, cost efficiency, and
performance
35

6.3 System Response
System response is based on cost, Sensitivity, accuracy, specificity, Fallout, TP, Recall, FP and
evaluation tools. System response in all the research papers is justified depending on the
decreased energy factors and display device. The minimized energy factors are fraud detection
technique, anomaly detection and classifier based detection. However, utilizing RF an LR model
isn’t that efficient to increase the system’s accuracy. But, utilizing GDBT could improvise the
system detecting the frauds in an effective way by Zhou, H., Chai, H. F., & Qiu, M. L., (2018).
Thus, the overall discussion identifies that most of the publications lack openness of display
device. There exists research papers which did not consider the network channel, but still shows
effective accuracy in credit card fraud detection.
7. Conclusion
“Fraud” refers to a big ethical problem in the modern world of Credit Card usage. These
Frauds are classified into several types. The frauds can occur in different and varied ways.
With the outcomes of application fraud, theft fraud, bankruptcy fraud, and behavioral
fraud will be the outcomes in the usage of the credit card transactions online and also in
the e-commerce field. The idea behind all these was to decrease the frauds faced by the
industry and how this should be reduced and eliminated to make the credit card usage as
safe and secured experience. Thus, the purpose of this research is to review and determine
the best algorithm to identify and limit the credit card frauds. Random Forest algorithm
has proved to be a winner in the tests and methodology that has been utilized for fraud
detection in comparison with the other algorithms like ANN, SVM etc. The main factors
looked in to the best algorithm includes accuracy and cost efficiency.The overall
components of this system were classified and described. This was followed by the system
classification, system evaluation and validation. Along with positive traits, the research
also presents few limitations like, it is difficult to review so many papers using the current
methodology. Though it helps to derive the points, it complicates the gather data and
increases confusion. However, the visualization technique was effective but, if one of the
part goes wrong then all the remaining evaluation and determination becomes waste.
The future research could include improving the features of the best algorithm. Based on
the research's findings it is requires advanced aggregation strategies, sequential, including
36

the non-sequential learning methods as they show varied and high difference results while
these manual aggregation strategies and sequential method. Different frauds and thefts can
be detected by these two approaches while using the subsequent evaluation of true
positives. But, even after all these progress and development, there is a long way to go to
fully resolve this issue and overcome the barriers of challenges in the form of practical
and scientific ways.
References
1) Aleskerov, E., Freisleben, B., & Rao, B. (2016). Cardwatch: A neural network based
database mining system for credit card fraud detection. In Proceedings of the IEEE/IAFE
1997 computational intelligence for financial engineering (CIFEr) (pp. 220–226). IEEE.
2) Baader, G., & Krcmar, H. (2018). Reducing false positives in fraud detection: Combining
the red flag approach with process mining. International Journal of Accounting
Information Systems, 31, 1-16. doi:https://doi.org/10.1016/j.accinf.2018.03.004
3) Bahnsen, A. C., Aouada, D., Stojanovic, A., & Ottersten, B. (2016). Feature engineering
strategies for credit card fraud detection. Expert Systems with Applications, 51, 134-142.
4) Carcillo, F., Le Borgne, Y. A., Caelen, O., & Bontempi, G. (2018). Streaming active
learning strategies for real-life credit card fraud detection: assessment and
visualization. International Journal of Data Science and Analytics, 5(4), 285-300.
5) Carneiro, N., Figueira, G., & Costa, M. (2017). A data mining based system for credit-
card fraud detection in e-tail. Decision Support Systems, 95, 91-101.doi:
http://dx.doi.org/10.1016/j.patrec.2017.08.024
6) Carta, S., Fenu, G., Recupero, D. R., & Saia, R. (2019). Fraud detection for E-commerce
transactions by employing a prudential Multiple Consensus model. Journal of
Information Security and Applications, 46, 13-22.
37

7) Choi, D., & Lee, K. (2018). An Artificial Intelligence Approach to Financial Fraud
Detection under IoT Environment: A Survey and Implementation. Security and
Communication Networks, 2018. doi: https://doi.org/10.1155/2018/5483472
8) Dal Pozzolo, A., Boracchi, G., Caelen, O., Alippi, C., & Bontempi, G. (2018). Credit
card fraud detection: a realistic modeling and a novel learning strategy. IEEE
transactions on neural networks and learning systems, 29(8), 3784-3797. doi:
10.1109/TNNLS.2017.2736643
9) de Sá, A. G., Pereira, A. C., & Pappa, G. L. (2018). A customized classification algorithm
for credit card fraud detection. Engineering Applications of Artificial Intelligence, 72, 21-
29. doi: https://doi.org/10.1016/j.engappai.2018.03.011
10) Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online
learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul),
2121–2159.
11) Fahmi, M., Hamdy, A., & Nagati, K. (2016). Data mining techniques for credit card fraud
detection: Empirical study. In BUE ACE1 sustainable vital technologies in engineering
and informatics (pp. 1–9).
12) Fan, J., Han, F., & Liu, H. (2017). Challenges of big data analysis. National Science
Review, 1(2), 293–314.
13) Fercoq, O., & Richtárik, P. (2018). Accelerated, parallel, and proximal coordinate
descent. SIAM Journal on Optimization, 25(4), 1997–2023.
http://dx.doi.org/10.1137/130949993.
14) Fiore, U., De Santis, A., Perla, F., Zanetti, P., & Palmieri, F. (2017). Using generative
adversarial networks for improving classification effectiveness in credit card fraud
detection. Information Sciences.
15) Fu, K., Cheng, D., Tu, Y., & Zhang, L. (2017, October). Credit card fraud detection using
convolutional neural networks. In International Conference on Neural Information
Processing(pp. 483-490). Springer, Cham.
16) Ganji, V. R., & Mannem, S. N. P. (2016). Credit card fraud detection using anti-k nearest
neighbor algorithm. International Journal on Computer Science and Engineering, 4(6),
1035-1039.
38

17) Gómez, J. A., Arévalo, J., Paredes, R., & Nin, J. (2018). End-to-end neural network
architecture for fraud scoring in card payments. Pattern Recognition Letters, 105, 175-
181. doi: http://dx.doi.org/10.1016/j.patrec.2017.08.024
18) Gruber, M., Schanes, C., Fankhauser, F., Grechenig, T., 2017. Voice calls for free: How
the black market establishes free phone calls – Trapped and uncovered by a VoIP
honeynet. In: Privacy, Security and Trust (PST), 2013 Proceedings of the Eleventh
Annual International Conference on, pp. 205–212. http://dx.doi.org/10.1109/PST.
2013.6596055.
19) Hoffstadt, D., Rathgeb, E., Liebig, M., Meister, R., Rebahi, Y., Thanh, T., 2017. A
comprehensive framework for detecting and preventing VoIP fraud and misuse. In:
Proceedings of the International Conference on Computing, Networking and
Communications (ICNC), pp. 807–813. http://dx.doi.org/10.1109/ICCNC.2014.
20) Hou, D., Cong, Y., Sun, G., Liu, J., & Xu, X. (2019). Anomaly detection via adaptive
greedy model. Neurocomputing, 330, 369-
379.doi:https://doi.org/10.1016/j.neucom.2018.09.080
21) Jiang, C., Song, J., Liu, G., Zheng, L., & Luan, W. (2018). Credit card fraud detection: A
novel approach using aggregation strategy and feedback mechanism. IEEE Internet of
Things Journal, 5(5), 3637-3647. doi: 10.1109/JIOT.2018.2816007
22) Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P., He-Guelton, L., &
Caelen, O. (2018). Sequence classification for credit-card fraud detection. Expert Systems
With Applications, 100, 234-245. doi: 10.1016/j.eswa.2018.01.037
23) Kim, E., Lee, J., Shin, H., Yang, H., Cho, S., & Nam, S. et al. (2019). Champion-
challenger analysis for credit card fraud detection: Hybrid ensemble and deep
learning. Expert Systems With Applications, 128, 214-224. doi:
10.1016/j.eswa.2019.03.042
24) Kültür, Y., & Çağlayan, M. U. (2017). Hybrid approaches for detecting credit card
fraud. Expert Systems, 34(2), e12191. doi: http://dx.doi.org/10.1016/j.cose.2015.09.005
25) M, S. (2009). Credit Card Fraud Detection : A Comparison using Random Forest, SVM
and ANN. International Research Journal Of Engineering And Technology
39

(IRJET), 06(03).
26) Manunza, L., Marseglia, S., & Romano, S. P. (2017). Kerberos: A real-time fraud
detection system for IMS-enabled VoIP networks. Journal of Network and Computer
Applications, 80, 22-34.
27) McGuinness, Deborah L. and Frank van Harmelen. 2018. “OWL Web Ontology
Language Overview.” https:// www.w3.org/TR/2004/REC-owl-features-20040210/
28) Nami, S., & Shajari, M. (2018). Cost-sensitive payment card fraud detection based on
dynamic random forest and k-nearest neighbors. Expert Systems with Applications.
doi:10.1016/j.eswa.2018.06.011.
29) Nisbet, R., Miner, G., Yale, K., Elder, J., & Peterson, A. (2018). Handbook of statistical
analysis and data mining applications (2nd ed.).
30) Niveditha, G., Abarna, K., & Akshaya, G. (2019). Credit Card Fraud Detection Using
Random Forest Algorithm. International Journal Of Scientific Research In Computer
Science, Engineering And Information Technology, 301-306. doi: 10.32628/cseit195261
31) Noy, Natalya Fridman, Ray W. Fergerson, and Mark A. Musen. 2018. “The Knowledge
Model of Protege2000: Combining Interoperability and Flexibility.” In Knowledge
Engineering and Knowledge Management Methods, Models, and Tools; 12th
International Conference, EKAW 2000 Juan-les-Pins, France, October 2-6, 2000
Proceedings, ed. Rose Dieng and Olivier Corby. Lecture Notes in Computer Science
1937. Berlin: Springer, 17-32.
32) Rajeshwari, U., & Babu, B. S. (2017, July). Real-time credit card fraud detection using
Streaming Analytics. In 2016 2nd International Conference on Applied and Theoretical
Computing and Communication Technology (iCATccT) (pp. 439-444). IEEE.
33) Randhawa, K., Loo, C. K., Seera, M., Lim, C. P., & Nandi, A. K. (2018). Credit card
fraud detection using AdaBoost and majority voting. IEEE access, 6, 14277-14284. doi:
10.1109/ACCESS.2018.2806420
34) Robinson, W. N., & Aria, A. (2018). Sequential fraud detection for prepaid cards using
hidden Markov model divergence. Expert Systems With Applications, 91 , 235–251.
40

35) Robinson, W. N., & Aria, A. (2018). Sequential fraud detection for prepaid cards using
hidden Markov model divergence. Expert Systems With Applications, 91, 235-251. doi:
http://dx.doi.org/10.1016/j.eswa.2017.08.043
36) Sahin, Y., Bulkan, S., & Duman, E. (2016). A cost-sensitive decision tree approach for
fraud detection. Expert Systems with Applications, 40(15), 5916-5923.
37) Save, P., Tiwarekar, P., Jain, K. N., & Mahyavanshi, N. (2017). A novel idea for credit
card fraud detection using decision tree. International Journal of Computer
Applications, 161(13).
38) Singh, K., & Upadhyaya, S. (2012). Outlier detection: applications and
techniques. International Journal of Computer Science Issues (IJCSI), 9(1), 307.
39) Srivastava, A., Kundu, A., Sural, S., & Majumdar, A. (2017). Credit card fraud detection
using hidden Markov model. IEEE Transactions on dependable and secure
computing, 5(1), 37-48.
40) Tang, X. B., Liu, G. C., Yang, J., & Wei, W. (2018). Knowledge-based Financial
Statement Fraud Detection System: Based on an Ontology and a Decision Tree. KO
KNOWLEDGE ORGANIZATION, 45(3), 205-219.
41) The Washington Post (2016). How artificial intelligence could stop those awkward
moments when your credit card is mistakenly declined
42) Van Vlasselaer, V., Bravo, C., Caelen, O., Eliassi-, T., Akoglu, L., Snoeck, M., et al.
(2017). APATE: a novel approach for automated credit card transaction fraud detection
using network-based extensions. Decision Support Systems, 75 , 38–48.
43) Vaughan, G. (2018). Efficient big data model selection with applications to fraud
detection. International Journal of Forecasting
44) Wang, C., & Han, D. (2018). Credit card fraud forecasting model based on clustering
analysis and integrated support vector machine. Cluster Computing, 1-6. doi:
https://doi.org/10.1007/s10586-018-2118-y
45) Wang, D., Chen, B., & Chen, J. (2018). Credit card fraud detection strategies with
consumer incentives. Omega. doi: https://doi.org/10.1016/j.omega.2018.07.001
46) Yee, O. S., Sagadevan, S., & Malim, N. H. A. H. (2018). Credit card fraud detection
41

using machine learning as data mining technique. Journal of Telecommunication,
Electronic and Computer Engineering (JTEC), 10(1-4), 23-27.
47) Ying, J. J. C., Zhang, J., Huang, C. W., Chen, K. T., & Tseng, V. S. (2018).
FrauDetector+: An Incremental Graph-Mining Approach for Efficient Fraudulent Phone
Call Detection. ACM Transactions on Knowledge Discovery from Data (TKDD), 12(6),
68. doi:10.1145/3234943
48) Zanin, M., Romance, M., Moral, S., & Criado, R. (2018). Credit card fraud detection
through parenclitic network analysis. Complexity, 2018. doi:
https://doi.org/10.1155/2018/5764370
49) Zareapoor, M., & Shamsolmoali, P. (2015). Application of credit card fraud detection:
Based on bagging ensemble classifier. Procedia Computer Science, 48, 679–685.
50) Zhang, J., Gardner, R., & Vukotic, I. (2019). Anomaly detection in wide area network
meshes using two machine learning algorithms. Future Generation Computer
Systems, 93, 418-426.
51) Zhao, X., Liang, X., Liu, L., Li, T., Han, Y., Vasconcelos, N., & Yan, S. (2016, October).
Peak-piloted deep network for facial expression recognition. In European conference on
computer vision (pp. 425-442). Springer, Cham.
52) Zheng, L., Liu, G., Yan, C., & Jiang, C. (2018). Transaction fraud detection based on
total order relation and behavior diversity. IEEE Transactions on Computational Social
Systems, (99), 1-11. doi: 10.1109/TCSS.2018.2856910
53) Zhou, H., Chai, H. F., & Qiu, M. L. (2018). Fraud detection within bankcard enrollment
on mobile device based payment using machine learning. Frontiers of Information
Technology & Electronic Engineering, 19(12), 1537-1545. doi:
https://doi.org/10.1631/FITEE.1800580
42