Fraud Detection Model Research Articles

An Intelligent Model for Online Recruitment Fraud Detection

This study research attempts to prohibit privacy and loss of money for individuals and organization by creating a reliable model which can detect the fraud exposure in the online recruitment environments. This research presents a major contribution represented in a reliable detection model using ensemble approach based on Random forest classifier to detect Online Recruitment Fraud (ORF). The detection of Online Recruitment Fraud is characterized by other types of electronic fraud detection by its modern and the scarcity of studies on this concept. The researcher proposed the detection model to achieve the objectives of this study. For feature selection, support vector machine method is used and for classification and detection, ensemble classifier using Random Forest is employed. A freely available dataset called Employment Scam Aegean Dataset (EMSCAD) is used to apply the model. Pre-processing step had been applied before the selection and classification adoptions. The results showed an obtained accuracy of 97.41%. Further, the findings presented the main features and important factors in detection purpose include having a company profile feature, having a company logo feature and an industry feature.

CORPORATE GOVERNANCE AND FRAUD DETECTION: A STUDY FROM BORSA ISTANBUL

Governments give high priority to corporate governance principles after important business scandals. Since the ultimate goal is to enable sustainable life span for the corporations, new regulations and sanctions has been introduced about transparency, and accountability all over the world. The basic corporate governance principles are applied for establishing more reliable financial reporting of firms. In this study, the relationship between corporate governance practices and fraud risk is investigated. There are some studies conducted in literature that investigating fraudulent financial statements, and detection models are tried to be constructed. They are generally based on financial indicators. The aim of this study is to combine financial data with non-financial variables about corporate governance applications, and to construct a fraud detection model via measuring the effectiveness of corporate governance on fraud risk. The hypotheses have been created based on assumptions and tested with the logistics regression. 134 companies listed in Istanbul Stock Exchange have been studied via benefiting their financial statements published between 2010 and 2014, and their corporate governance applications announced. Findings show that the new regulations about corporate governance principles and their applications in Turkey have not made the expected effect on fraud risk yet. On the other hand, profitability and indebt positions of companies have an impact on the risk of preparing fraudulent financial statements, and give clues about the misstatements, consistently with literature.

Cooperative Fraud Detection Model With Privacy-Preserving in Real CDR Datasets

The researchers have shown broad concern about detection and recognition of fraudsters since telecommunication operators and the individual user are both suffering significant losses from fraud activities. Researchers have proposed various solutions to counter fraudulent activity. However, those methods may lose effectiveness in fraud detection because fraudsters always tend to cover their tracks by roaming among different telecommunication operators. What is more, due to the lack of real data, researchers have to do simulations in a virtual scenario, which makes their models and results less persuasive. In our previous paper, we proposed a novel strategy with high accuracy and security through cooperation among mobile telecommunication operators. In this manuscript, we will validate it in a real-world scenario using real Call Detail Records(CDR) data. We apply the Latent Dirichlet Allocation (LDA) model to profile users. Then we use a method based on Maximum Mean Discrepancy (MMD) to compare the distribution of samples to match roaming fraudsters. Cooperation between telecommunication operators may boost the accuracy of detection while the potential risk of privacy leakage exists. A strategy based on Differential Privacy(DP) is used to address this problem. We demonstrate that it can detect the fraudsters without revealing private data. Our model was validated using simulated dataset and showed its effectiveness. In this manuscript, experiments are performed on real CDRs data, and the result shows that our method has impressive performance in the real-world scenario as well.

Rasio-Rasio Keuangan dalam Memprediksi Kecurangan

Penlitian ini bertujuan untuk membuktikan apakah perusahaan yang melakukan kecurangan akuntansi dengan yang tidak melakukan kecurangan akuntansi memiliki nilai rasio yang berbeda secara signifikan dengan menggunakan dua model pendeteksi kecurangan akuntansi yaitu Beneish M-Score da Altman Z-Score. Penelitian ini menggunakan delapan variabel yaitu debt to equity ratio , debt to total asset ratio, net profit to revenue ratio, current asset to total asset ratio, receivable to revenue ratio, inventory to total asset ratio,working capital to total asset ratio dan revenue to total asset ratio.
 Populasi dari penelitian ini adalah perusahaan manufaktur yang terdaftar di Bursa Efek Indonesia periode 2010-2016. Total sampel dalam penelitian ini sebanyak 57 perusahaan dengan jumlah observasi sebanyak 212. Pengujian hipotesis dengan menggunakan uji beda independent sample t-test.
 Hasil penelitian ini menunjukkan bahwa variabel debt to equity ratio , debt to total asset ratio, net profit to revenue ratio, working capital to total asset ratio dan revenue to total asset ratio memiliki perbedaan yang signifikan antara perusahaan yang melakukan kecurangan akuntansi dengan yang tidak melakukan kecurangan akuntansi. Sedangkan untuk variabel current asset to total asset ratio, receivable to revenue ratio , dan inventory to total asset ratio tidak memiliki perbedaan yang signifikan antara perusahaan yang melakukan kecurangan akuntansi dengan yang tidak melakukan kecurangan akuntansi.

The Comprehensive Model of Whistle-Blowing, Forensic Audit, Audit Investigation, and Fraud Detection

Fraud is a problem that has never been resolved from year to year. One type of fraud that often occurs in the government sector is corruption. Various attempts have been made by the government to detect fraud, but the efforts that have been made have not been effective in reducing fraud. This study aims to propose a conceptual model for detecting fraud by linking whistle-blowing, forensic audits, and investigation audits. The conceptual model of this research is expected to provide input to managers and decision makers regarding the factors that need to be considered in improving fraud detection so that in the future fraud prevention methods will be better and better.

An Effective Financial Statements Fraud Detection Model

The purpose of this study is to establish an effective and rigorous financial statements fraud (FSF) detection model. The samples of this study are the listed companies in Taiwan, totaling 220 companies and including 55 companies with financial statements fraud and 165 normal companies. The data are from the Taiwan Economic Journal (TEJ) during the period from 2006 to 2015. In Stage I, decision tree CART and artificial neural network (ANN) are applied to select the important variables. In Stage II, decision tree CHAID, ANN, and support vector machine (SVM) are used for modeling. The results show that the ANN-CHAID model has the highest FSF detection accuracy of 87.41%.

A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection

Using wireless mobile terminals has become the mainstream of Internet transactions, which can verify the identity of users by passwords, fingerprints, sounds, and images. However, once these identity data are stolen, traditional information security methods will not avoid online transaction fraud. The existing convolutional neural network model for fraud detection needs to generate many derivative features. This paper proposes a fraud detection model based on the convolutional neural network in the field of online transactions, which constructs an input feature sequencing layer that implements the reorganization of raw transaction features to form different convolutional patterns. Its significance is that different feature combinations entering the convolution kernel will produce different derivative features. The advantage of this model lies in taking low dimensional and nonderivative online transaction data as the input. The whole network consists of a feature sequencing layer, four convolutional layers and pooling layers, and a fully connected layer. Verifying with online transaction data from a commercial bank, the experimental results show that the model achieves excellent fraud detection performance without derivative features. And its precision can be stabilized at around 91% and recall can be stabilized at around 94%, which increased by 26% and 2%, respectively, comparing with the existing CNN for fraud detection.

Parallel and incremental credit card fraud detection model to handle concept drift and data imbalance

Real-time fraud detection in credit card transactions is challenging due to the intrinsic properties of transaction data, namely data imbalance, noise, borderline entities and concept drift. The advent of mobile payment systems has further complicated the fraud detection process. This paper proposes a transaction window bagging (TWB) model, a parallel and incremental learning ensemble, as a solution to handle the issues in credit card transaction data. TWB model uses a parallelized bagging approach, incorporated with an incremental learning model, cost-sensitive base learner and a weighted voting-based combiner to effectively handle concept drift and data imbalance. Experiments were performed with Brazilian Bank data and University of California, San Diego (UCSD) data, and results were compared with state-of-the-art models. Comparisons on Brazilian Bank data indicates increased fraud detection levels between 18–38% and 1.3–2 times lower cost levels, which exhibits the enhanced performances of TWB. Comparisons on UCSD data indicate improved precision levels ranging between 8 and 25%, indicating the robustness of the TWB model. Future extensions of the proposed model will be on incorporating feature engineering to improve performances.

Cost-sensitive payment card fraud detection based on dynamic random forest and k-nearest neighbors

Payment card fraud leads to heavy annual financial losses around the world, thus giving rise to the need for improvements to the fraud detection systems used by banks and financial institutions. In the academe, as well, payment card fraud detection has become an important research topic in recent years. With these considerations in mind, we developed a method that involves two stages of detecting fraudulent payment card transactions. The extraction of suitable transactional features is one of the key issues in constructing an effective fraud detection model. In this method, additional transaction features are derived from primary transactional data. A better understanding of cardholders’ spending behaviors is created by these features. After which the first stage of detection is initiated. A cardholder's spending behaviors vary over time so that new behavior of a cardholder is closer to his/her recent behaviors. Accordingly, a new similarity measure is established on the basis of transaction time in this stage. This measure assigns greater weight to recent transactions. In the second stage, the dynamic random forest algorithm is employed for the first time in initial detection, and the minimum risk model is applied in cost-sensitive detection. We tested the proposed method on a real transactional dataset obtained from a private bank. The results showed that the recent behavior of cardholders exerts a considerable effect on decision-making regarding the evaluation of transactions as fraudulent or legitimate. The findings also indicated that using both primary and derived transactional features increases the F-measure. Finally, an average 23% increase in prevention of damage (PoD) is achieved with the proposed cost-sensitive approach.

A hybrid mobile call fraud detection model using optimized fuzzy C-means clustering and group method of data handling-based network

A novel two-stage fraud detection system in mobile telecom networks has been presented in this paper that identifies the malicious calls among the normal ones in two stages. Initially, a genetic algorithm-based optimized fuzzy c-means clustering is applied to the user’s historical call records for constructing the calling profile. Thereafter, the identification of the fraudulent calls occurs in two stages. In the first stage, each incoming call is passed to the clustering module that identifies the call as genuine, malicious or suspicious. This is done by comparing the distance value of the new calling instance from the profile cluster centers against two predefined threshold values. The calls detected as genuine or malicious are not further processed. However, the call records that are found to be suspicious are additionally scrutinized in the second stage by a previously trained group method of data handling model for final decision making. The legitimate and forged labeled call records generated out of the clustering module are utilized for training the supervised classifier. Experimentation is done on a real-world call dataset to exhibit the effectiveness of the proposed model. A comparative analysis of the current approach with one of our earlier propositions and another recent fraud detection system clearly illustrates the efficacy of the developed model.

An Effective Financial Statements Fraud Detection Model for the Sustainable Development of Financial Markets: Evidence from Taiwan

This study aims to establish a rigorous and effective model to detect enterprises’ financial statements fraud for the sustainable development of enterprises and financial markets. The research period is 2004–2014 and the sample is companies listed on either the Taiwan Stock Exchange or the Taipei Exchange, with a total of 160 companies (including 40 companies reporting financial statements fraud). This study adopts multiple data mining techniques. In the first stage, an artificial neural network (ANN) and a support vector machine (SVM) are deployed to screen out important variables. In the second stage, four types of decision trees (classification and regression tree (CART), chi-square automatic interaction detector (CHAID), C5.0, and quick unbiased efficient statistical tree (QUEST)) are constructed for classification. Both financial and non-financial variables are selected, in order to build a highly accurate model to detect fraudulent financial reporting. The empirical findings show that the variables screened with ANN and processed by CART (the ANN + CART model) yields the best classification results, with an accuracy of 90.83% in the detection of financial statements fraud.

Offsite Detection of Insider Abuse and Bank Fraud among U.S. Failed Banks 1989-2015

We find evidence that material insider abuse and internal fraud were present in approximately 457 (37 percent) of the 1,237 U.S. failed commercial and mutual savings banks (hereafter, banks) between 1989 and 2015. Using a unique dataset of the incidence of insider abuse and internal fraud among U.S. failed banks we analyze the characteristics of failed banks with the ultimate goal of developing fraud detection models — parametric (logistic regression, Benford digit analysis) and non-parametric (neural networks). We obtain information on the incidence of insider abuse and internal fraud among failed banks from failing bank cases prepared for the FDIC Board of Directors, restitution orders (fines) supervisors assessed for bank employee fraud, and bond claims the FDIC made to recover fraud-related losses on failed banks. The supervisory data we use to quantify fraud among failed banks has not been used previously in published research and, we feel, provides more comprehensive information on fraud among failed banks than that available to academic researchers. Since fraudulent behavior lies outside the realm of rationale behavior modelled in economics, we develop a framework for internal bank fraud that provides rationale and support for our fraud detection models. This framework is based on previous studies of financial fraud and internal bank fraud in particular. We test this framework using regression analysis of the determinants of fraudulent behavior among failed banks between 1989 and 2015 and find that banks with insider abuse and fraud present overstated income and asset values, under-reported losses and consequently overstated net worth. The regression models of fraudulent failed banks provide information on the financial statement line items that can be used to identify fraud. We next use a recently developed second-order Benford digit test to identify those banks whose financial statements suggest tampering and purposeful misstatement. Our results suggest that material insider abuse and fraud at banks is detectable using Benford digit analysis of bank financial data for a period one-to-four years prior to failure. Unfortunately, we are unable to develop an accurate neural network model for fraud prediction.

Detection and Solutions for Non-Technical Losses in Cameroon Electricity Network

The purpose of this study was to provide a tool to detect NTLs and subsequently, discuss the establishment of a prepaid system in Cameroon. The conception of a prepayment system for electric power or other utility commodity distribution using Wi-Fi and GSM to store and transfer value (money or KWh, meters reading indexes) from the client module to cut-off module then to platform of the system and deliver power to the customer from the power distribution system. This system is also used as fraud detection model for the Cameroon National Electricity Company.

Leveraging deep learning with LDA-based text analytics to detect automobile insurance fraud

Automobile insurance fraud represents a pivotal percentage of property insurance companies' costs and affects the companies' pricing strategies and social economic benefits in the long term. Automobile insurance fraud detection has become critically important for reducing the costs of insurance companies. Previous studies on automobile insurance fraud detection examined various numeric factors, such as the time of the claim and the brand of the insured car. However, the textual information in the claims has rarely been studied to analyze insurance fraud. This paper proposes a novel deep learning model for automobile insurance fraud detection that uses Latent Dirichlet Allocation (LDA)-based text analytics. In our proposed method, LDA is first used to extract the text features hiding in the text descriptions of the accidents appearing in the claims, and deep neural networks then are trained on the data, which include the text features and traditional numeric features for detecting fraudulent claims. Based on the real-world insurance fraud dataset, our experimental results reveal that the proposed text analytics-based framework outperforms a traditional one. Furthermore, the experimental results show that the deep neural networks outperform widely used machine learning models, such as random forests and support vector machine. Therefore, our proposed framework that combines deep neural networks and LDA is a suitable potential tool for automobile insurance fraud detection.

English

This paper proposes a multi-algorithm strategy for card fraud detection. Various techniques in data mining have been used to develop fraud detection models; it was however observed that existing works produced outputs with false positives that wrongly classified legitimate transactions as fraudulent in some instances; thereby raising false alarms, mismanaged resources and forfeit customers’ trust. This work was therefore designed to develop a hybridized model using an existing technique Density-Based Spatial Clustering of Applications with Noise (DBSCAN) combined with a rule base algorithm to reinforce the accuracy of the existing technique. The DBSCAN algorithm combined with Rule base algorithm gave a better card fraud prediction accuracy over the existing DBSCAN algorithm when used alone. Key words: Card fraud detection, density-based spatial clustering of applications with noise (DBSCAN), rule base algorithm, data mining.

An Inference Model of Medical Insurance Fraud Detection: Based on Ontology and SWRL

An Inference Model of Medical Insurance Fraud Detection: Based on Ontology and SWRL

Bayesian multinomial latent variable modeling for fraud and abuse detection in health insurance

Healthcare fraud and abuse are a serious challenge to healthcare payers and to the entire society. This article presents a predictive model for fraud and abuse detection in health insurance based on a training dataset of manually reviewed claims. The goal of the analysis is to predict different fraud and abuse probabilities for new invoices. The prediction is based on a wide framework of fraud and abuse reports which examine the behavior of medical providers and insured members by measuring systematic deviation from usual patterns in medical claims data. We show that models which directly use the results of the reports as model covariates do not exploit the full potential in terms of predictive quality. Instead, we propose a multinomial Bayesian latent variable model which summarizes behavioral patterns in latent variables, and predicts different fraud and abuse probabilities. The estimation of model parameters is based on a Markov Chain Monte Carlo (MCMC) algorithm using Bayesian shrinkage techniques. The presented approach improves the identification of fraudulent and abusive claims compared to different benchmark approaches.

A Novel Machine Learning Approach to Credit Card Fraud Detection

The use of credit cards is of paramount importance in improving the economic strength of any nation, however, fraudulent activities associated with it is of great concern. When fraud occurs on credit cards, the negative impact is huge as the financial loss experienced cuts across all the parties involved. This paper provides a proactive measure at detecting fraudulent activities regarding the credit card. A novel approach in machine learning known as the cortical learning algorithm was adopted to build the credit card fraud detection model. The algorithm worked on the credit card data obtained from the UCI Repository, it converted the highly populated data to a sparse representation, and then used its learning columns to learn spatial and temporal patterns. The object oriented analysis and design methodology was used in the design of the system which was implemented with JAVA programming language. The simulation was carried out with Matlab. The resulting model performed online learning and recorded higher percentage accuracy of 91% and beyond in detecting fraudulent transactions as compared to the Neural Network model that recorded 89.6%, hence, cases of misclassification was reduced to the barest minimum and efficiency of fraud detection was increased.

A Bayesian Classification Model for Fraud Detection over ATM Platforms

A Bayesian Classification Model for Fraud Detection over ATM Platforms

Feature engineering strategies for credit card fraud detection

Every year billions of Euros are lost worldwide due to credit card fraud. Thus, forcing financial institutions to continuously improve their fraud detection systems. In recent years, several studies have proposed the use of machine learning and data mining techniques to address this problem. However, most studies used some sort of misclassification measure to evaluate the different solutions, and do not take into account the actual financial costs associated with the fraud detection process. Moreover, when constructing a credit card fraud detection model, it is very important how to extract the right features from the transactional data. This is usually done by aggregating the transactions in order to observe the spending behavioral patterns of the customers. In this paper we expand the transaction aggregation strategy, and propose to create a new set of features based on analyzing the periodic behavior of the time of a transaction using the von Mises distribution. Then, using a real credit card fraud dataset provided by a large European card processing company, we compare state-of-the-art credit card fraud detection models, and evaluate how the different sets of features have an impact on the results. By including the proposed periodic features into the methods, the results show an average increase in savings of 13%.