Credit risk has been a widespread and deep penetrating problem for centuries, but not until various credit derivatives and products were developed and novel technologies began radically changing the human society, have fraud detection, credit scoring and other risk management systems become so important not only to some specific firms, but to industries and governments worldwide. Frauds and unpredictable defaults cost billions of dollars each year, thus, forcing financial institutions to continuously improve their systems for loss reduction. In the past twenty years, amounts of studies have proposed the use of data mining techniques to detect frauds, score credits and manage risks, but issues such as data selection, algorithm design, and hyperparameter optimization affect the perceived ability of the proposed solutions and it is difficult for auditors and researchers to explore and figure out the highest level of general development in this area. In this survey we focus on a state of the art survey of recently developed data mining techniques for fraud detection and credit scoring. Several outstanding experiments are recorded and highlighted, and the corresponding techniques, which are mostly based on supervised learning algorithms, unsupervised learning algorithms, semisupervised algorithms, ensemble learning, transfer learning, or some hybrid ideas are explained and analysed. The goal of this paper is to provide a dense review of up-to-date techniques for fraud detection and credit scoring, a general analysis on the results achieved and upcoming challenges for further researches.

/pdf/a-state-of-the-art-survey-of-data-mining-based-fraud-ardforust6.pdf

A state of the art survey of data mining-based fraud detection and credit scoring

Credit card fraud is increasing considerably with the development of modern technology and the global superhighways of communication. Credit card fraudsters continuously try to come out with a new tactic challenged the present technology and system. It cost both, providers and consumers a lot of money. Thus, quick and accurate model become essential for companies and credit card providers, to decrease their financial and customer trust losses. However, there is a lack of published literature on credit card fraud detection techniques, due to the unlabeled credit card transactions dataset for researchers. High dimensional data refer to data that have multiple variables. The dataset consist of the credit card details, amount transaction, location, time, and personal details of the cardholders that are anonymized. Thus, in this study, a real-world dataset (European Credit card), with PCA transformation applied is being used. The common problem happened in this kind of research is the data tend to be imbalanced. Imbalanced data will often introduce bias which the accuracy of the prediction is not accurate. In this study, the dataset has been train with an oversampling pre-processing technique called SAS Sample and various data mining technique such as Random Forest, KNN, Decision Tree, and Logistic Regression. After several trials, we found out that the regression technique has the best performance among the others.

/pdf/predicting-credit-card-fraud-on-a-imbalanced-data-2vhbej0mal.pdf

Predicting Credit Card Fraud on a Imbalanced Data

Majority vote ensemble classifier for accurate detection of credit card frauds

Purpose – The best algorithm that was implemented on this Brazilian dataset was artificial immune system (AIS)
algorithm. But the time and cost of this algorithm are high. Using asexual reproduction optimization (ARO) algorithm,
the authors achieved better results in less time. So the authors achieved less cost in a shorter time. Their framework
addressed the problems such as high costs and training time in credit card fraud detection. This simple and effective
approach has achieved better results than the best techniques implemented on our dataset so far. The purpose of this
paper is to detect credit card fraud using ARO.
Design/methodology/approach – In this paper, the authors used ARO algorithm to classify the bank transactions
into fraud and legitimate. ARO is taken from asexual reproduction. Asexual reproduction refers to a kind of production in
which one parent produces offspring identical to herself. In ARO algorithm, an individual is shown by a vector of variables.
Each variable is considered as a chromosome. A binary string represents a chromosome consisted of genes. It is supposed
that every generated answer exists in the environment, and because of limited resources, only the best solution can remain
alive. The algorithm starts with a random individual in the answer scope. This parent reproduces the offspring named bud.
Either the parent or the offspring can survive. In this competition, the one which outperforms in fitness function remains
alive. If the offspring has suitable performance,it will be the next parent, and the current parent becomes obsolete.Otherwise,
the offspring perishes, and the present parent survives. The algorithm recurs until the stop condition occurs.
Findings – Results showed that ARO had increased the AUC (i.e. area under a receiver operating characteristic (ROC)
curve), sensitivity, precision, specificity and accuracy by 13%, 25%, 56%, 3% and 3%, in comparison with AIS,
respectively. The authors achieved a high precision value indicating that if ARO detects a record as a fraud, with a high
probability, it is a fraud one. Supporting a real-time fraud detection system is another vital issue. ARO outperforms AIS
not only in the mentioned criteria, but also decreases the training time by 75% in comparison with the AIS, which is a
significant figure.
Originality/value – In this paper, the authors implemented the ARO in credit card fraud detection. The authors
compared the results with those of the AIS, which was one of the best methods ever implemented on the benchmark
dataset. The chief focus of the fraud detection studies is finding the algorithms that can detect legal transactions from
the fraudulent ones with high detection accuracy in the shortest time and at a low cost. That ARO meets all these
demands.

/pdf/credit-card-fraud-detection-using-asexual-reproduction-4560zxirko.pdf

Credit card fraud detection using asexual reproduction optimization

Fraud is a costly business problem which causes every organization to face huge loss. Fraud may lead to risk of financial loss and loss of the confidence of customers and stakeholders of the company. Cyber security teams and internal audit departments of most of the organizations try to monitor such fraudulent activities using traditional rule-based fraud detection systems. However, with the rapid adaptation of online financial transactions, it is more difficult to identify fraudulent activities by static methods and via data analysis. Further, as traditional rule-based fraud detection systems cannot dynamically adjust the rule set based on the behavioral changes of the fraudsters, there is a high possibility of detecting false positive alerts. The aim of this paper is to review selected machine learning techniques where it can be used to develop a fraud detection system which identifies fraudulent activities in financial transactions.

Monetary Transaction Fraud Detection System Based on Machine Learning Strategies

The most acknowledged payment mode is credit card for both disconnected and online mediums in today's day and age. It facilitates cashless shopping everywhere in the world. It is the most widespread and reasonable approach with regards to web based shopping, paying bills, what's more, performing other related errands. Thus danger of fraud exchanges utilizing credit card has likewise been expanding. In the Current Fraud Detection framework, false exchange is recognized after the transaction is completed. As opposed to the current system, the proposed system presents a methodology which facilitates the detection of fraudulent exchanges while they are being processed, this is achieved by means of Behaviour and Locational Analysis(Neural Logic) which considers a cardholder's way of managing money and spending pattern. A deviation from such a pattern will then lead to the system classifying it as suspicious transaction and will then be handled accordingly.

https://iopscience.iop.org/article/10.1088/1757-899X/263/4/042039/pdf

Credit card fraud detection using neural network and geolocation

A Green city enables the perfect usage of resources and more dependable quality of services to the masses. To supply inspection and repairs such as air quality management, weather monitoring and automation of homes and edifices in a smart city, the basic parameters are humidity, water level temperature, gas level. This task delivers a customized blueprint of an Internet of Things (IoT) enabled environment monitoring system to monitor temperature, water point, humidity and gas level. In developed system, information is transmitted from the transmitter tx node to the receiver rx node using the Bluetooth sensor module. The data received at the receiver node is entered in a database and is monitored as logs into a personal data processor (PC) through an Arduino IDE. An Android application has also been broken through which information is transferred from Arduino IDE to a smartphone, for monitoring data remotely. The settlements and the carrying out of the proposed strategy is discussed.

Real Time Weather Monitoring using Internet of Things

Wireless Sensor Networks contain an incredible number of hubs with limited registering, detecting, and wireless communication capacities. These systems have been utilized as a part of a wide zone of utilizations, such as human services, contamination checking, and target-following frameworks. The dynamic clustering of sensors into bunches is a prevalent procedure to expand the system lifetime and increment adaptability. To accomplish this, in this article the sensor hubs are adjusted to ensure a long lifetime and the activities are arranged into rounds that use fixed time intervals. In the first phase, a clustering topology is found, and a group head is picked in view of the outstanding energy level. Then the cluster head screens the network energy threshold value to identify the energy drain rate of all its cluster members. In the second stage, the Long-Lifetime and Low-Latency Data Aggregation Scheduling method is used. This scheduling method assigns schedule openings to group part information parcels. Here, congestion occurrence is completely kept away from the scenario. In the third stage, an Energy-Efficient Distributed Schedule–based convention is used to keep up greatest residual energy level over the network. The experimental outcome shows the steps proposed in this article ensure an increase in the network lifetime and decrease in the energy utilization.

Long-Lifetime and Low Latency Data Aggregation Scheduling for Wireless Sensor Network

With the evolution of social media, information sharing in online is turning into ubiquitous each and every day. Various facts are propagating thru online social networks along with each the wonderful and negative. In this paper, our essential focal point is to resolve terrible or incorrect data such as rumors. Rumor is a serious problem in online social media. The wrong rumors can create many problems in society; hence, it is important to block these rumors. First in this paper, we have compared Naive Bayes algorithm and logistic regression for deciding which algorithm is better for spam classification. Then, we have proposed a model for detecting spammers in twitters and automatically blocking those rumors by hindering an assured subset of the nodes. In order to decrease the influence of the rumors, nodes are allotted an acceptance time threshold. If a user posts the rumor more than a particular threshold, the user gets automatically blocked. We have created a Java-based Web application using tomcat SQL server, JavaScript html and CSS, like Facebook where a user can search for friends, accept friend requests, chat with them, change profile pictures and post messages. In this paper, we used a supervised learning technique known as Naive Bayes Algorithm for blocking of the users. The analysis of users blocked per month can be also done which will help in study of users and rumor details.

An Analysis of Machine Learning Approach for Detecting Automated Spammer in Twitter

In this study, we discuss three DTN routing protocols, these are epidemic, PRoPHET and spray and wait routing protocols. A special simulator will be used; that is opportunistic network environment (ONE) to create a network environment. Spray and wait has highest delivery rate and low latency in most of the cases. Hence, spray and wait have better performance than others. This analysis of the performance of DTN protocols helps the researcher to learn better of these protocols in the different environment.,Delay-Tolerant Network (DTN) is a network designed to operate effectively over extreme distances, such as those encountered in space communications or on an interplanetary scale. In such an environment, nodes are occasional communication and are available among hubs, and determinations of the next node communications are not confirmed. In such network environment, the packet can be transferred by searching current efficient route available for a particular node. Due to the uncertainty of packet transfer route, DTN is affected by a variety of factors such as packet size, communication cost, node activity, etc.,Spray and wait have highest delivery rate and low latency in most of the cases. Hence, spray and wait have better performance than others.,The primary goal of the paper is to extend these works in an attempt to offer a better understanding of the behavior of different DTN routing protocols with delivery probability, latency and overhead ratio that depend on various amounts of network parameters such as buffer size, number of nodes, movement ratio, time to live, movement range, transmission range and message generation rate. In this study, we discuss three DTN routing protocols: these are epidemic, PRoPHET and spray and wait routing protocols. A special simulator will be used; that is opportunistic network environment (ONE) to create a network environment. Spray and wait have highest delivery rate and low latency in most of the cases. Hence, spray and wait have better performance than others. This analysis of the performance of DTN protocols helps the researcher to learn better of these protocols in the different environment.

R. Mangayarkarasi

Papers

Credit card fraud detection using neural network and geolocation

Real Time Weather Monitoring using Internet of Things

Long-Lifetime and Low Latency Data Aggregation Scheduling for Wireless Sensor Network

An Analysis of Machine Learning Approach for Detecting Automated Spammer in Twitter

A comparative study on delay-tolerant network routing protocols