Fraud Patterns Research Articles

RaKShA: A Trusted Explainable LSTM Model to Classify Fraud Patterns on Credit Card Transactions

Credit card (CC) fraud has been a persistent problem and has affected financial organizations. Traditional machine learning (ML) algorithms are ineffective owing to the increased attack space, and techniques such as long short-term memory (LSTM) have shown promising results in detecting CC fraud patterns. However, owing to the black box nature of the LSTM model, the decision-making process could be improved. Thus, in this paper, we propose a scheme, RaKShA, which presents explainable artificial intelligence (XAI) to help understand and interpret the behavior of black box models. XAI is formally used to interpret these black box models; however, we used XAI to extract essential features from the CC fraud dataset, consequently improving the performance of the LSTM model. The XAI was integrated with LSTM to form an explainable LSTM (X-LSTM) model. The proposed approach takes preprocessed data and feeds it to the XAI model, which computes the variable importance plot for the dataset, which simplifies the feature selection. Then, the data are presented to the LSTM model, and the output classification is stored in a smart contract (SC), ensuring no tampering with the results. The final data are stored on the blockchain (BC), which forms trusted and chronological ledger entries. We have considered two open-source CC datasets. We obtain an accuracy of 99.8% with our proposed X-LSTM model over 50 epochs compared to 85% without XAI (simple LSTM model). We present the gas fee requirements, IPFS bandwidth, and the fraud detection contract specification in blockchain metrics. The proposed results indicate the practical viability of our scheme in real-financial CC spending and lending setups.

Wangiri Fraud: Pattern Analysis and Machine-Learning-Based Detection

The rapid growth of the telecommunication landscape leads to a rapid rise of frauds in such networks. In this article, Wangiri fraud in which users are deceived by being charged for services without their knowledge during a call is tackled. In fact, Wangiri fraud has significant negative financial and reputation consequences for the mobile service providers and also has a bad psychological impact on the victims. In order to identify this fraudulent behavior, three Wangiri fraud patterns are defined by analyzing call records of over a year. Then, the security and performance of unsupervised and supervised machine learning (ML) methods in detecting one Wangiri pattern are evaluated using a large real-world Call Detail Records (CDRs) data set. In the context of Wangiri fraud detection, classification algorithms outperformed the others based on the chosen security and performance metrics. Finally, the performance evaluation of these algorithms is extended in detecting the other two real-world Wangiri fraud patterns. This article provides a detailed definition of the Wangiri fraud patterns and outlines the implementation and evaluation of ML algorithms in the context of detecting Wangiri fraud. The security analysis and experimental results demonstrate that depending on fraud patterns the best ML algorithm to detect Wangiri fraud may also vary.

How big data analytics is used in forensic accounting and auditing

In this study, we investigate the application of big data analytics in forensic accounting and auditing. Big data technology mediates the connection between awareness and plans to use for fraud detection. We made an effort to assess how big data might be used in forensic accounting and auditing practices. Design/methodology This research is based on systematic literature review, and it provides a thorough understanding of the existing literature on big data research in forensic accounting and auditing. The research was gathered through peer-reviewed literature using current (post-2014) articles. Results/findings The model for corporate auditing has changed. Managers at the organization are proactively identifying and resolving internal abnormalities and discrepancies prior to an external audit using conventional audit techniques. Known white-collar crimes at several publicly traded corporations have led to a high demand for forensic accountants. Big data analytics is a key tool for spotting fraud patterns. Students should be encouraged to develop skills in data generation, sharing, analytics, mining, reporting, and storage because big data analytics is essential to business education. Practical implications and conclusions The study's conclusions can be applied to the forensic accounting industry to assist in the development of Big Data fraud-fighting technology. Big data analytics and forensic accounting should be covered in accounting curricula. By offering different perspectives on big data and its practical implications in accounting practice, this research contributes to the body of published knowledge. As more companies use big data, the need to update the accounting curriculum is highlighted because success now requires a distinct set of skills. Future research should involve interviewing and surveying accountants, auditors, and other members of the financial services industry, which will be difficult but necessary.

LongArms: Fraud Prediction in Online Lending Services Using Sparse Knowledge Graph

Gang fraud, the major and primary security issue in online lending services, can be efficiently solved by the data-driven paradigm that is recognized as a promising solution for online lending gang fraud prediction. However, it is challenging that such predictions need to detect evolving and increasingly impalpable fraud patterns based on low-quality data, i.e., very preliminary and coarse applicant information. The technical difficulty mainly stems from two factors: the extreme <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">deficiency of information associations</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">weakness of data labels</i> . In this work, we mainly address the challenges by enhancing the utility of associations (i.e., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">recovering missing associations</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mining underlying associations</i> ) on a knowledge graph. Specifically, we first propose an efficient method of Chinese address disambiguation to recover some critical associations that are broken by the ambiguity of applicant information, e.g., address related information. Then, to mine the implicit associations, we design a novel association representation method, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Adaptive Connected Component Embedding Simplification Scheme</i> (ACCESS), which can adaptively implement embedding for different connected components depending on their sizes. Finally, we adopt the graph clustering algorithms and devised predicting schemes based on the above enhanced associations to predict gang fraud in the case of weakness of data labels. Moreover, we propose a framework called RMCP by integrating the above techniques, which is consists of four steps: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Recovering</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Mining</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Clustering</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Predicting</i> , for efficiently predicting gang fraud. The good performance is validated by the experiments on a real-world dataset from a commercial lending company. Meanwhile, we provide a visual decision support system named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LongArms</i> over the RMCP framework.

Data Analytics and Predictive Modeling for Toll Violation Prevention

This study aims to utilize data analytics and predictive modeling techniques to prevent toll violations. By analyzing various sources of data such as travel datasets, unstructured data, and financial data, the study will develop algorithms that can accurately predict toll violations and identify potential fraud patterns. The research, which utilized unstructured data, points to the utility of data mining which would greatly benefit traffic research, particularly African-based studies, that suffer from data inadequacy. The study will also explore the use of machine learning algorithms to decipher the large textual data contained in transportation research papers. Additionally, the study will investigate the accuracy and performance of different predictive algorithms, such as linear regression, analysis of variance, and artificial neural networks, in predicting toll violations based on various factors such as category, purpose, total distance, and speed of travel. Furthermore, the study will examine the forensic aspects of big data in order to enhance the capabilities of forensic investigators in case of a network attack. In today’s rapidly changing world, the significance of accurate toll violation prevention using data analytics and predictive modeling techniques cannot be overstated. In today’s rapidly changing world, the significance of accurate toll violation prevention using data analytics and predictive modeling techniques cannot be overstated. By leveraging data analytics and predictive modeling, this study aims to develop an effective toll violation prevention system

Covid-19 Pandemic and Online Fraud: Malaysian Experience

The main objective of this study is to examine how the Covid-19 outbreak has affected online fraud in Malaysia. In particular, this study aims to provide a conceptual discussion as well as a comparison analysis of online fraud patterns prior to and during the Covid-19 outbreak. This study uses police recorded online fraud data to provide comparison between pre and during the Covid-19 pandemic. This study period is 2018-2019 and 2020-2021. Results indicate that most online fraud categories increased dramatically during the Covid-19 outbreak. In particular, the number of online frauds associated with e-commerce and online investment, which are the most common online fraud categories in Malaysia, have seen the largest increasing rates between the two periods. The findings of this study provide preliminary evidences on the increasing of online fraud in the country and can motivate researcher to investigate on the factors that affect such frauds.

Framework for Detection of Fraud at Point of Sale on Electronic Commerce sites using Logistic Regression

Many businesses have been positively impacted by electronic commerce (ecommerce). It has enabled enterprises and consumers transact business digitally and experience diversity as long as the internet is accessible and there is a gadget to surf the internet. Several governments have gradually adopted electronic payment throughout the country. The Nigerian government has also done a lot of prodding toward the adoption of a cashless economy, which includes embracing ecommerce. As ecommerce expands, so does actual and attempted fraud through this channel. According to the Nigerian Central Bank, electronic fraud reached trillions of Naira by 2021. The purpose of this work was to employ logistic regression as a decision-making tool for detecting fraud in e-commerce platforms at either the virtual or physical point of sale. The main contribution of this research is a model developed using logistic regression for detecting fraud at the point of sale on electronic commerce platforms. The accuracy of the result is 97.8 percent. The result of this study will provide key decision makers in ecommerce firms with information on fraud patterns on their ecommerce platforms, this will enable them take quick actions to forestall these fraudulent attempts. Further research should be carried out using data from other developing countries.

Detecting Anomalies in Financial Data Using Machine Learning Algorithms

Bookkeeping data free of fraud and errors are a cornerstone of legitimate business operations. The highly complex and laborious work of financial auditors calls for finding new solutions and algorithms to ensure the correctness of financial statements. Both supervised and unsupervised machine learning (ML) techniques nowadays are being successfully applied to detect fraud and anomalies in data. In accounting, it is a long-established problem to detect financial misstatements deemed anomalous in general ledger (GL) data. Currently, widely used techniques such as random sampling and manual assessment of bookkeeping rules become challenging and unreliable due to increasing data volumes and unknown fraudulent patterns. To address the sampling risk and financial audit inefficiency, we applied seven supervised ML techniques inclusive of deep learning and two unsupervised ML techniques such as isolation forest and autoencoders. We trained and evaluated our models on a real-life GL dataset and used data vectorization to resolve journal entry size variability. The evaluation results showed that the best trained supervised and unsupervised models have high potential in detecting predefined anomaly types as well as in efficiently sampling data to discern higher-risk journal entries. Based on our findings, we discussed possible practical implications of the resulting solutions in the accounting and auditing contexts.

Dynamics of Dark Web Financial Marketplaces: An Exploratory Study of Underground Fraud and Scam Business

The number of Dark Web financial marketplaces where Dark Web users and sellers actively trade illegal goods and services anonymously has been growing exponentially in recent years. The Dark Web has expanded illegal activities via selling various illicit products, from hacked credit cards to stolen crypto accounts. This study aims to delineate the characteristics of the Dark Web financial market and its scams. Data were derived from leading Dark Web financial websites, including Hidden Wiki, Onion List, and Dark Web Wiki, using Dark Web search engines. The study combines statistical analysis with thematic analysis of Dark Web content. Offering promotions and customer services with the payment methods of cryptocurrencies were prevalent, similar to the Surface Web's e-commerce market. The findings suggest that the Dark Web financial market is likely to harbor scams targeting Dark Web buyers. Dark Web sellers construct a website to sell scam products and recommend purchasing Escrow services to ensure safe transactions as an additional scam. The results from this study provided empirical support for the components of the routine activity theory of the Dark Web financial market to substantiate a more comprehensive view of patterns of fraud/ scams. Enhancing law enforcement capabilities of investigating financial marketplaces and promoting public awareness and consumer safety programs are discussed as effective preventive measures.

Sequential Pattern Mining Approach for Personalized Fraudulent Transaction Detection in Online Banking

Financial institutions face challenges of fraud due to an increased number of online transactions and sophisticated fraud techniques. Although fraud detection systems have been implemented to detect fraudulent transactions in online banking, many systems just use conventional rule-based approaches. Rule-based detection systems have a difficulty in updating and managing their rules and conditions manually. Additionally, generated from the few fraud cases, the rules are general rather than specific to each user. In this paper, we propose a personalized alarm model to detect frauds in online banking transactions using sequence pattern mining on each user’s normal transaction log. We assumed that a personalized fraud detection model is more effective in responding to the rapid increase in online banking users and diversified fraud patterns. Moreover, we focused on the fact that fraudulent transactions are very different from each user’s usual transactions. Our proposed model divides each user’s log into transactions, extracts a set of sequence patterns, and uses it to determine whether a new incoming transaction is fraudulent. The incoming transaction is divided into multiple windows, and if the normal patterns are not found in the consecutive windows, an alarm is sounded. We applied the model to a real-world dataset and showed that our model outperforms the rule-based model and the Markov chain model. Although more experiments on additional datasets are needed, our personalized alarm model can be applied to real-world systems.

Consumer Fraud in Online Shopping: Detecting Risk Indicators through Data Mining

ABSTRACT Consumer fraud in online shopping has become a major problem and severe challenge for online retailers. However, detection lags behind — for academia and practice — and data-driven knowledge about risk indicators in transaction data is still very limited. Thus, this study focuses on the empirical data-based identification of consumer fraud risk indicators and combinations in online shopping transaction data. We demonstrate the use of a decision tree as a data mining technique for analysis of data from one of the world’s largest online retailers. Thereby, several patterns of fraud that improve separation of online shopping transactions into fraudulent and legitimate cases are identified. Thus, results can guide the choice of variables and design of fraud prevention actions and systems in future practical and theoretical work.

ATOVis – A visualisation tool for the detection of financial fraud

Fraud detection is related to the suppression of possible financial losses for institutions and their clients. It is a task of high responsibility and, therefore, an important phase of the decision-making chain. Nowadays, experts in charge base their analysis on tabular data, usually presented in spreadsheets and seldom supplemented with simple visualisations. However, this type of inspection is laborious, time-consuming, and may be of little use for the analysis and overview of complex transactional data. To aid in the inspection of fraudulent activities, we develop ATOVis – a visualisation tool that enables a fast analysis and detection of suspicious behaviours. We aim to ease and accelerate fraud detection by providing an overview of specific patterns within the data, and enabling details on demand. ATOVis focuses on applying visualisation techniques to the Finance domain, specifically e-commerce, contributing to the state-of-the-art as the first visualisation tool primarily specialised in Account Takeover (ATO) patterns. In particular, the present paper incorporates: a task abstraction for detecting a specific financial fraud pattern – ATO; two models for the visualisation of ATO; and a multiscale timeline to enable an overview of the data. We also validate our tool through user testing, with experts in fraud detection and experts from other fields of data science. Based on the feedback provided by the analysts, we could conclude that ATOVis is an efficient and effective tool in detecting specific patterns of fraud which can improve the analysts’ work.

Financial statement fraud in Indonesia: a longitudinal study of financial misstatement in the pre- and post-establishment of financial services authority

Purpose This study aims to investigate cases of fraudulent financial statements that have occurred in Indonesia and explore the similarities of cases that existed in the period before and after the establishment of the Financial Services Authority. Design/methodology/approach This paper provides a descriptive examination of financial misstatements issued by different regimes by listed companies of the capital market and financial institution supervisory agency and the introduction of new financial service authority; among 93 listed companies that were subject to an official investigation arising from the publication of financial misstatements, these assessments were facilitated by mean of content analysis of annual reports following the announcement of an investigation. Findings The findings indicate that each regime has a specific pattern of financial statement fraud. It is found that senior management is responsible for most fraud, and recording a fictitious sale is the most common method of falsifying financial statements. Under the new regime, the publication of cases is limited since the introduction of risk-based supervision. Financial Services Authority is likely to fine and prosecute the director of a company as a perpetrator rather than a corporation as a legal entity. Originality/value This study contributes to the literature on the incidence of financial statement fraud in public companies and provides a detailed descriptive comparison of cases scrutinized by securities exchange commission in an emerging country.

EFraudCom: An E-commerce Fraud Detection System via Competitive Graph Neural Networks

With the development of e-commerce, fraud behaviors have been becoming one of the biggest threats to the e-commerce business. Fraud behaviors seriously damage the ranking system of e-commerce platforms and adversely influence the shopping experience of users. It is of great practical value to detect fraud behaviors on e-commerce platforms. However, the task is non-trivial, since the adversarial action taken by fraudsters. Existing fraud detection systems used in the e-commerce industry easily suffer from performance decay and can not adapt to the upgrade of fraud patterns, as they take already known fraud behaviors as supervision information to detect other suspicious behaviors. In this article, we propose a competitive graph neural networks (CGNN)-based fraud detection system (eFraudCom) to detect fraud behaviors at one of the largest e-commerce platforms, “Taobao” 1 . In the eFraudCom system, (1) the competitive graph neural networks (CGNN) as the core part of eFraudCom can classify behaviors of users directly by modeling the distributions of normal and fraud behaviors separately; (2) some normal behaviors will be utilized as weak supervision information to guide the CGNN to build the profile for normal behaviors that are more stable than fraud behaviors. The algorithm dependency on fraud behaviors will be eliminated, which enables eFraudCom to detect fraud behaviors in presence of the new fraud patterns; (3) the mutual information regularization term can maximize the separability between normal and fraud behaviors to further improve CGNN. eFraudCom is implemented into a prototype system and the performance of the system is evaluated by extensive experiments. The experiments on two Taobao and two public datasets demonstrate that the proposed deep framework CGNN is superior to other baselines in detecting fraud behaviors. A case study on Taobao datasets verifies that CGNN is still robust when the fraud patterns have been upgraded.

COMPARATIVE ANALYSIS OF CLASSIFICATION TECHNIQUES FOR CREDIT CARD FRAUD DETECTION

Nowadays, in the global computing environment, online payments are a necessary evil as it makes payment conveniently easier and can be done via an ample of available options like a Credit card, Debit Card, Net Banking, PayPal, Paytm available to make payments easier. The most common mode of payment used in online shopping is Credit Card as it is easier for the customers to directly transfer money from one account to another; without the withdrawal of cash at any point. However, this easy payment mode has opened up paths for multiple frauds which involve theft or illegal tampering of data of the credit card owner. Thus, with the increasing number of fraud cases and losses, it is important to find the best solution to detect credit card fraud as well as minimize the number of frauds in online systems. With the analysis of different sets of research performed on the given problem statement, we have concluded that the issue requires a substantial amount of predictions and application of machine learning to find the accuracy score of those commonly used algorithms to predict which of these three state-of-art-algorithms - Naive Bayes, Logistic Regression and K Neighbours, is best suitable to carry out the research in this area. In order to support our findings, we apply two different approaches i.e. with sampling and without sampling on these algorithms against the same dataset. We claim on the basis of our results that K Neighbours outperformed all in both the approaches and is more suitable to carry forward the fraud detection research using machine learning. The analysis will be useful for those working to derive anti-fraud strategies to predict the fraud patterns and reduce the risk during hefty transactions.

Internal control of accounting of fixed assets in accordance with the new standards

Abstract. The purpose. Study of the peculiarities of the organization of the internal control system of fixed assets in order to reduce the risks of ineffective use and theft. Research methods. Analyzed normative acts, explanations of regulatory authorities, judicial practice. Particular attention is paid to the analysis of federal accounting standards governing the accounting of fixed assets, which come into effect from 2022. Results. Changes in regulations governing the procedure for conducting accounting and tax accounting require adjustments and methods of verification by internal controllers. Fixed assets are components of the material and technical base of the enterprise, allow increasing sales, producing quality products and increasing attractiveness in the eyes of investors. The introduction of new accounting standards, as well as the strengthening of administration by the regulatory authorities, require a revision of internal local documents and changes to the internal control methods. The directions of the organization of internal control of fixed assets, practical examples of incorrect reflection in the accounting of assets and the consequences leading to additional taxes are considered. The risks of theft and ineffective use of fixed assets arise from both managers and employees of the enterprise. Properly organized internal control will help identify fraud patterns and reduce the risks of damage to the enterprise. The paper proposes step-by-step algorithms for organizing internal control for the main business operations associated with the use of fixed assets. Namely, the algorithm for checking the accrued depreciation, repair costs, documents confirming the liquidation of fixed assets. Errors made in the formation of the initial cost can lead to a distortion of the cost, the book value of fixed assets and lead to an incorrect calculation of income tax and property tax of organizations.

Credit Card Fraud Detection Using Deep Learning Based on Auto-Encoder

Fraudulent activities in financial fields are continuously rising. The fraud patterns tend to vary with time, and no consistency can be observed in this regard. The incorporation of new technology by fraudsters is the reason for the execution of online fraud transactions. Given the volatility of the fraud patterns, a good fraud detection model must be able to evolve and update itself to the changing patterns. Thus we aim in this paper to analyze the fraud cases that are unable to be detected based on supervised learning or previous history, create an Auto-encoder model based on deep learning and Compare and assess the performance of the model based on data from different parts of the world and check for the demographic diversity of fraud patterns thereby inferring that the data from which part of the world the model fits the best. The proposed algorithm, deep learning based on the auto-encoder (AE) network is an unsupervised learning algorithm that utilizes backpropagation by setting the inputs and outputs identical. In this research, the Tensorflow package from Google has been employed to implement AE by using deep learning. The accuracy, precision, recall, F1 score and area under the curve(AUC) are all executed to assess the performance of the model.

Exploring the Risky Travel Area and Behavior of Car-hailing Service

Recent years have witnessed the rapid development of car-hailing services, which provide a convenient approach for connecting passengers and local drivers using their personal vehicles. At the same time, the concern on passenger safety has gradually emerged and attracted more and more attention. While car-hailing service providers have made considerable efforts on developing real-time trajectory tracking systems and alarm mechanisms, most of them only focus on providing rescue-supporting information rather than preventing potential crimes. Recently, the newly available large-scale car-hailing order data have provided an unparalleled chance for researchers to explore the risky travel area and behavior of car-hailing services, which can be used for building an intelligent crime early warning system. To this end, in this article, we propose a Risky Area and Risky Behavior Evaluation System (RARBEs) based on the real-world car-hailing order data. In RARBEs, we first mine massive multi-source urban data and train an effective area risk prediction model, which estimates area risk at the urban block level. Then, we propose a transverse and longitudinal double detection method, which estimates behavior risk based on two aspects, including fraud trajectory recognition and fraud patterns mining. In particular, we creatively propose a bipartite graph-based algorithm to model the implicit relationship between areas and behaviors, which collaboratively adjusts area risk and behavior risk estimation based on random walk regularization. Finally, extensive experiments on multi-source real-world urban data clearly validate the effectiveness and efficiency of our system.

Guest Editorial: Special Section on Embracing Artificial Intelligence for Network and Service Management

Artificial Intelligence (AI) has the potential to leverage the immense amount of operational data of clouds, services, and social and communication networks. As a concrete example, AI techniques have been adopted by telcom operators to develop virtual assistants based on advances in natural language processing (NLP) for interaction with customers and machine learning (ML) to enhance the customer experience by improving customer flow. Machine learning has also been applied to finding fraud patterns which enables operators to focus on dealing with the activity as opposed to the previous focus on detecting fraud.

Management and reduction of fraud by analysis of the insurer’s internal and external vulnerabilities and contributions

"Fraud is a dynamic phenomenon: when the industry discovers a „scam” – a specific pattern of fraud – and sets up barriers to prevent it from recurring, another scam takes place – a new pattern is developed by fraudsters. The motivations for committing fraud vary: from opportunists who submit a fraudulent request as a way to recover their insurance premium, probably encouraged by a change in public attitudes towards crime without victims to criminal networks that use fraud as a regular source of revenue generation. The legal, organizational and commercial constraints under which the insurance industry operates often have a negative impact on existing fraud prevention, detection and investigation practices. Initially, the fight against insurance fraud focused on identifying the characteristics of fraudulent claims and fraudulent claimants – the empirical phase / traditional approach and the role that insurance company employees played in this phase was a major one. Then, given the wave of interest in the insurance industry, emphasis was placed on the use of approaches such as: a) cognitive interviewing and vocal stress analysis that were used in forensic investigation, as well; b) data extraction techniques, specially developed for fraud detection. Are just these effective? The material will try to analyze the vulnerabilities and contributions, both internal and external, that are introduced by the policies, procedures and controls implemented by the insurer within the organization."