Fraud Patterns Research Articles

An intelligent sequential fraud detection model based on deep learning

Fraud detection and prevention has received a lot of attention from the research community due to its high impact on financial institutions’ revenues and reputation. The increased use of the web and the provision of online services open up the pathway for exposing these systems to numerous threats and jeopardizing their effective functioning. Naturally, financial frauds are increased in number and form imposing various requirements for their efficient and immediate detection. These requirements are related to the performance of the adopted models as well as the timely response of the decision-making mechanism. Machine learning and data mining are two research domains that can provide a number of techniques/algorithms for fraud detection and setup the road for mitigation actions. However, these methods still need to be improved with respect to the detection of unknown fraud patterns and the incorporation of big data processing mechanisms. This paper presents our attempt to build a hybrid system, i.e., a sequential scheme for combining two deep learning models and efficiently detecting potential financial frauds. We elaborate on the combination of an autoencoder and a Long Short-Term Memory Recurrent Neural Network trained upon datasets which are processed through the use of an oversampling technique. Oversampling is adopted to handle heavily imbalanced datasets which is the ‘natural’ scenario due to the limited number of frauds compared to the humongous volumes of transactions. The proposed approach tends to capture much more fraud events in comparison with other conventional ML techniques. Our experimental evaluation exposes that our model exhibits a good performance in terms of recall and precision.

Pre-trained Online Contrastive Learning for Insurance Fraud Detection

Medical insurance fraud has always been a crucial challenge in the field of healthcare industry. Existing fraud detection models mostly focus on offline learning scenes. However, fraud patterns are constantly evolving, making it difficult for models trained on past data to detect newly emerging fraud patterns, posing a severe challenge in medical fraud detection. Moreover, current incremental learning models are mostly designed to address catastrophic forgetting, but often exhibit suboptimal performance in fraud detection. To address this challenge, this paper proposes an innovative online learning method for medical insurance fraud detection, named POCL. This method combines contrastive learning pre-training with online updating strategies. In the pre-training stage, we leverage contrastive learning pre-training to learn on historical data, enabling deep feature learning and obtaining rich risk representations. In the online learning stage, we adopt a Temporal Memory Aware Synapses online updating strategy, allowing the model to perform incremental learning and optimization based on continuously emerging new data. This ensures timely adaptation to fraud patterns and reduces forgetting of past knowledge. Our model undergoes extensive experiments and evaluations on real-world insurance fraud datasets. The results demonstrate our model has significant advantages in accuracy compared to the state-of-the-art baseline methods, while also exhibiting lower running time and space consumption. Our sources are released at https://github.com/finint/POCL.

Predicting likelihood of fraud among financial distressed firms in Malaysia using textual analysis

This research paper aims to analyze and predict fraud patterns among failed companies in Malaysia. The approach involves utilizing textual analysis on the management discussion and analysis (MD&A) section within the annual reports. The dataset is subjected to text clustering to group companies based on similar financial characteristics. This clustering process entails several steps, including data conversion, collation, and summarization into a structured format, followed by text pre-processing to cleanse the dataset. Notably, RapidMiner Studio software was utilized to extract data for the study. Subsequently, the documents are clustered using both the K-means and latent dirichlet allocation (LDA) methods. Upon examining a sample of 22 failed companies in the year 2020, the study reveals that financially distressed companies exhibit prominent financial negativity and utilize litigious financial terms within their MD&A sections. These linguistic traits are found to be closely associated with seven distinct characteristics of fraudulent firms. This preliminary findings provide compelling evidence that financial pressure may serve as a triggering factor for fraudulent activities within companies.

Financial Fraud Identification Model of Listed Companies based on Time-Series Information

The aim of this research is to establish a high-precision financial fraud identification model for listed companies, which is mainly based on the financial indicators of time series. Support vector machine and K-means clustering algorithm are especially used in the research process. Firstly, local linear embedding is used to reduce the dimensionality of the selected financial indicators to extract the low-dimensional characteristics. Then the samples are classified into financial fraud and non-fraud by support vector machine, and the recognition model is constructed. At the same time, the research also uses K-means clustering algorithm to analyze the pattern of financial fraud. The experiment of dimensionality reduction proves that the model has a high effect on the processing of financial data, and the error between the data after dimensionality reduction and the original data is small. In addition, the clustering effect of the model also shows a clear pattern of fraud. In practical application, the accuracy rate of this model is as high as 94.89%, showing high accuracy and recall rate, and its F1 value is 87.08%, showing its feasibility and effectiveness in practice. The results highly prove that the performance of the financial fraud identification model proposed in this study is excellent, and it has a wide application prospect in the future.

Explainable fraud detection of financial statement data driven by two-layer knowledge graph

In modern economic activities, financial statement fraud will seriously mislead the economic decisions of investors and regulators, and will lead to huge investment losses even corporate bankruptcies. Although the powerful abilities have been gained by current machine learning methods in financial statement fraud detection problems, the explainability and the ability of extracting fraudulent patterns are still very scarce. In this study, an explainable Financial Statement data Fraud Detection method is proposed by introducing a Two-Layer Knowledge Graph (FSFD-TLKG) and a fraudulent pattern mining strategy on two-layer knowledge graph. Wherein, a two-layer knowledge graph comprises a semantic layer and a syntactic layer. Concretely, the subordination relationships among financial variables are represented in the semantic layer, and their articulation relationships are represented in the syntactic layer. Moreover, an explainable approach is designed to extract financial statement fraudulent patterns for credible fraud assertion. Experimental results show that, FSFD-TLKG can effectively extract explainable financial statement fraudulent patterns and obtain better detection accuracy than almost all traditional machine learning and deep learning methods except an unexplainable method: Extreme Gradient Boosting (XGBoost). Even for XGBoost, the explainable financial statement fraudulent patterns extracted by our method still can further improve its performance. Clearly, FSFD-TLKG gains the optimal practical performance which is much better than existing methods.

ANALISIS KECURANGAN DALAM MENGHADAPI PENIPUAN DI SITUS E-COMMERCE MENGGUNAKAN RANDOM FOREST ; PENDEKATAN MACHINE LEARNING BERBASIS AI

In this rapidly growing digital era, the phenomenon of e-commerce has become a major highlight, the rapid growth of e-commerce has attracted more and more users. However, cases of sophisticated and dynamic fraud are increasing as the volume of transactions increases. This phenomenon not only poses a risk of financial loss for buyers and sellers but also threatens the trust that is so important in the e-commerce industry. To solve this problem, the author uses a random Forest AI-based Machine Learning approach in analyzing and finding fraud patterns to deal with fraud on e-commerce sites. The Random Forest model was chosen because of its excellent ability to handle complex e-commerce transaction data, including the ability to find non-linear patterns, its resistance to overfitting, and its scalability on large datasets. This model is expected to identify suspicious fraud patterns in e-commerce transactions. The method will involve data processing, feature selection, and model training using a dataset that includes ecommerce transactions. The results of this research are expected to contribute to a better understanding of fraud on e-commerce sites in the face of future fraud. Effective fraud detection is also expected to reduce the losses caused by fraud on e-commerce sites and protect users from the risk of fraud.

Investigating Purchase and Transaction Fraud on the Internet among Youth Individuals: A Comprehensive Study Employing Fraudulent Patterns and Statistical Analysis

Investigating Purchase and Transaction Fraud on the Internet among Youth Individuals: A Comprehensive Study Employing Fraudulent Patterns and Statistical Analysis

Boosting Financial Fraud Detection Using Parameter Tuned Ensemble Machine Learning Model

Fraud detection in the financial industry is a challenging area as financial transactions gradually shift to digital platforms. More and more businesses such as the financial industry are operationalizing their services online as the usage of the internet is growing exponentially. Accordingly, financial fraud can increase in number and forms worldwide leading to remarkable financial losses that make financial fraud a main challenge. Threats such as irregular attacks and unauthorized access must be identified through a financial fraud detection system. Over the past few years, data mining and machine learning (ML) approaches have been widely used to address these issues. However, this technique has yet to be enhanced in terms of speed computation, identifying unknown attack patterns, and dealing with big data. This study presents Financial Fraud Detection using the Parameter Tuned Ensemble Machine Learning (FFD-PTEML) method. The FFD-PTEML incorporates multiple advanced components, such as z-score normalization for feature scaling and ensemble classification employing Artificial Neural Networks (ANN), Multilayer Perceptron (MLP), and Radial Basis Function (RBF) networks. The use of z-score normalization ensures uniformity in feature distribution, improving the effectiveness and interpretability of the fraud detection technique. Furthermore, the ensemble classification model combines the strength of different neural network architectures to enhance the detection performance and resilience to complicated fraud patterns. FFD-PTEML demonstrates better performance than the classical technique through extensive experimentation on real-time financial datasets, exhibiting high sensitivity and specificity in fraudulent activity detection.

CUSTOMS FRAUD DETECTION USING EXTREMELY BOOSTED NEURAL NETWORK (XBNET)

Noticing the vital role of cross-border trade has made Customs plays a crucial role not only in maintaining supply chain but also in securing government revenue from intentional fraud. Given the huge volume of international trade and limited workforce, Customs across the world must implement efficient and effective risk management. This paper proposes XBNet, an ensemble of tree-based algorithms with deep learning algorithms, to detect fraud in import activity. The strength of XBNet is combining gradient-boosted trees with neural networks where the weights, bias, and loss are adjusted simultaneously with the importance features of each tree in each layer. The object of this study is Import Declaration data from four Customs Offices, and the model is set for each Customs office to capture fraud patterns related to their region. We compared the model with two different parameters and concluded the models with learning rates = 1%, number of hidden layers = 2, activation function = sigmoid, and number of epochs = 100 as the most suitable for the Belawan, Merak, and Makassar and model with number of hidden layers = 2, number of epochs = 50 and other parameters are set the same as the most suitable for Tanjung Emas.

Machine Learning In Fraud Detection and Prevention

Digital fraud has become a threat to businesses of all kinds. Under the IOT scenario, financial fraud refers to unauthorized mobile transactions using mobile platforms to fraudulently obtain funds through identity theft or credit card theft It has now become imperative for an organization to pay attention emphasize fraud and people suppression. Digitization has revolutionized the daily tasks we perform at the click of a button. In the real world, financial fraud detection under the IOT scenario requires advanced planning since financial fraud results in financial loss. Thus, we primarily analyzed financial fraud mechanisms using machine learning and deep learning techniques such as complex algorithms for fraud pattern detection. But fraudsters are also becoming smarter by the day and must be constantly monitored to prevent fraud and stay ahead of fraudsters. It is important to look at salient patterns that can help distinguish genuine behavior from fraudulent behavior. Client information such as Geo-location, authentication, session, and device IP address can be captured and monitored. The application of machine learning and artificial intelligence will play an ever-important role in detecting and identifying fraudulent patterns.

Public Procurement Nexus Social for Mitigate the Corruption: Lesson from Indonesia

This study delves into the vulnerability of Indonesia's National Budget (APBN) to corruption, specifically in the Procurement of Goods and Services, with a particular focus on the potential for misallocation across regions. Building on significant scholarly contributions from both Indonesian and international researchers, the research undertakes a thorough examination of preventive measures against corruption in public procurement. Employing a Participatory Action Research (PAR) approach, the study integrates community solidarity into its corruption prevention model, utilizing a combination of data collection methods such as questionnaires, interviews, and focus group discussions (FGDs). A central topic in the study is the important role of e-procurement in combating corruption, advocating for its transparent and accountable application as a deterrent. To bolster preventive efforts, the research proposes mandatory declarations from tender participants, along with an enhanced auction rebuttal mechanism throughout the various stages of procurement. The preventative framework underscores the significance of civilian, academic, and journalistic supervision to proactively identify corruption and conflicts of interest. Recognizing the nuanced nature of fraud patterns at the provincial level, the study advocates for a region-specific approach to maximize the effectiveness of e-procurement. This regional focus aligns with the study's emphasis on the involvement of relevant agencies operating at the local level. In essence, this research contributes a targeted analysis to complement existing literature, aiming to curb corruption in public procurement through strategic and context-specific preventive measures.

An Empirical Analysis of Machine Learning for Fraud Detection in Diverse Financial Scenarios

Fraud detection is important in various domains. As fraud patterns become complex, it is critical to develop accurate and efficient detection systems based on machine learning. However, in different scenarios, there are different key points for fraud detection, and the best model and important features of machine learning may also be different. Therefore, this study aims to explore the relationship between the key points in each scenario and the best model and important features of machine learning corresponding to the scenario. This research firstly used scikit-learn to perform machine learning on the datasets of three different scenarios, online payment, credit card, bank account, and find out important features to analyze the applicability of machine learning models in different scenarios and the reasons behind it. Based on the characteristics of each kind of data, the machine learning model and the characteristics of the fraud itself in different scenarios, exploring the explain ability of combining machine learning with human knowledge. The study found that Light GBM is suitable for all scenarios, because it can capture complex relationships in data, and its high efficiency of dealing with imbalanced data. The research identifies distinct important features of each domain combined with human knowledge, provides insight into potentially fraudulent activity. This will provide a certain theoretical basis for developing a more accurate and efficient fraud detection system, improving the performance of human-computer interaction in the system, or applying the human-in-the-loop model.

Research on Financial Fraud Detection Models Integrating Multiple Relational Graphs

The current fraud risk in digital finance is increasing year by year, and the mainstream solutions rely on the inherent characteristics of users, which makes it difficult to explain fraud behaviors and fraud behavior patterns are less researched. To address these problems, we propose an integrated multiple relational graphs fraud detection model Tri-RGCN-XGBoost, which analyzes the impact of user association patterns on fraud detection by mining the behavioral associations of users. The model builds a heterogeneous information network based on real transaction data, abstracts three types of bipartite graphs (user–device, user–merchant, and user–address), aggregates the information of the user’s neighbor nodes under the three types of behavioral patterns, and integrates the graph convolution classification results under the three behavioral patterns with the XGBoost model to achieve fraudulent user detection with integrated multiple relational graphs. The results show that the performance of this model in fraud identification is significantly improved, especially in reducing the fraudulent user underreporting rate. Further, the behavioral associations that play a key role in fraud user identification are analyzed in conjunction with shape value to provide a reference for fraud pattern mining.

Beyond the individual: An improved telecom fraud detection approach based on latent synergy graph learning

The development of telecom technology not only facilitates social interactions but also inevitably provides the breeding ground for telecom fraud crimes. However, telecom fraud detection is a challenging task as fraudsters tend to commit co-fraud and disguise themselves within the mass of benign ones. Previous approaches work by unearthing differences in calling sequential patterns between independent fraudsters, but they may ignore synergic fraud patterns and oversimplify fraudulent behaviors. Fortunately, graph-like data formed by traceable telecom interaction provides opportunities for graph neural network (GNN)-based telecom fraud detection methods. Therefore, we develop a latent synergy graph (LSG) learning-based telecom fraud detector, named LSG-FD, to model both sequential and interactive fraudulent behaviors. Specifically, LSG-FD introduces (1) a multi-view LSG extractor to reconstruct synergy relationship-oriented graphs from the meta-interaction graph based on second-order proximity assumption; (2) an LSTM-based calling behavior encoder to capture the sequential patterns from the perspective of local individuals; (3) a dual-channel based graph learning module to alleviate the disassortativity issue (caused by the camouflages of fraudsters) by incorporating the dual-channel frequency filters and the learnable controller to adaptively aggregate high- and low-frequency information from their neighbors; (4) an imbalance-resistant model trainer to remedy the graph imbalance issue by developing a label-aware sampler. Experiment results on the telecom fraud dataset and another two widely used fraud datasets have verified the effectiveness of our model.

Dynamic Resilience in Credit Card Fraud Detection: The Adaptive Accuracy Weighted Ensemble Approach

This paper introduces the Adaptive Accuracy Weighted Ensemble (AAWE) algorithm, strategically devised to fortify credit card fraud detection against the constant threat of concept drift. Centered on the foundational Multilayer Perceptron (MLP) classifier, AAWE seamlessly incorporates dynamic weighting mechanisms to skillfully acclimate to the ever-shifting landscape of fraudulent activities. This innovative progression substantiates AAWE's capacity to substantially augment the precision of credit card fraud detection, demonstrating adeptness in negotiating the intricate challenges presented by perpetually evolving fraudulent strategies. In the realm of credit card fraud detection, wherein subtle deviations in fraud methodologies can yield profound consequences, AAWE's intrinsic adaptability emerges as a pivotal asset. The algorithm's ability to promptly respond to concept drift nuances becomes a critical edge. With empirical evidence showcasing its commendable accuracy rates, AAWE emerges as a compelling remedy to the exigent concept drift quandary within credit card fraud detection. This research sheds a compelling light on AAWE's potential to deliver robust and pinpoint-accurate fraud detection outcomes, solidifying its stature as an invaluable instrument for real-world scenarios where timely accommodation to emerging fraud patterns is of paramount significance.

The Role of Forensic Accounting in Bridging the Audit Expectation Gap of Microfinance Banks in Akwa Ibom State

The audit expectation gap has widened due to the occurrence of undetected high-profile financial statement frauds, highlighting the need for effective measures to address this issue. This study investigated the role of forensic accounting in bridging the expectation gap among stakeholders in microfinance banks in Akwa Ibom State. Using a survey research design, primary data were collected from 128 respondents representing a sample size drawn from ten randomly selected microfinance banks in Uyo. The data were analyzed using Pearson’s correlation coefficient statistical tool. The findings indicated that incorporating forensic accounting skills significantly mitigates corporate financial fraud by promptly detecting fraudulent patterns that traditional audits may overlook. This highlighted the importance of forensic accounting in addressing the limitations of conventional audit practices. Based on the results, the researcher concluded that forensic accounting practice plays a crucial role in bridging the audit expectation gaps of microfinance banks. To enhance financial reporting quality and stakeholder confidence, it was recommended that microfinance bank directors engage auditors equipped with requisite forensic accounting skills. This proactive approach will enable the early detection and effective mitigation of fraudulent financial reporting, ultimately leading to the production of qualitative financial reports that meet stakeholder expectations.

TgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs

Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose TgrApp, which extracts carefully designed features and provides visualizations to assist analysts in spotting fraudsters and suspicious behavior. Our TgrApp method has the following properties: (a) Scalable, as it is linear on the input size; and (b) Effective, as it allows natural interaction with human analysts, and is applicable in both supervised and unsupervised settings.

Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation

Credit card fraud incurs a considerable cost for both cardholders and issuing banks. Contemporary methods apply machine learning-based classifiers to detect fraudulent behavior from labeled transaction records. But labeled data are usually a small proportion of billions of real transactions due to expensive labeling costs, which implies that they do not well exploit many natural features from unlabeled data. Therefore, we propose a semi-supervised graph neural network for fraud detection. Specifically, we leverage transaction records to construct a temporal transaction graph, which is composed of temporal transactions (nodes) and interactions (edges) among them. Then we pass messages among the nodes through a Gated Temporal Attention Network (GTAN) to learn the transaction representation. We further model the fraud patterns through risk propagation among transactions. The extensive experiments are conducted on a real-world transaction dataset and two publicly available fraud detection datasets. The result shows that our proposed method, namely GTAN, outperforms other state-of-the-art baselines on three fraud detection datasets. Semi-supervised experiments demonstrate the excellent fraud detection performance of our model with only a tiny proportion of labeled data.

Fraudulent Banking Transaction Classification Using Deep Learning Algorithm.

Financial fraud is a significant problem in the banking industry, and detecting fraudulent transactions is a critical task for banks to protect their customers and maintain trust in the financial system. Traditional rule-based approaches for detecting fraud often rely on pre-defined thresholds and heuristics, which can be circumvented by sophisticated fraudsters. As a result, machine learning techniques have gained increasing attention in recent years for their ability to automatically learn from data and adapt to changing fraud patterns .In this project, we propose a novel approach for classifying fraudulent banking transactions using a deep learning algorithm. Our approach leverages the power of deep neural networks to automatically extract meaningful features from transaction data, and then use these features to accurately classify transactions as either fraudulent or legitimate

Credit Card Fraudulent Transaction Detection and Prevention

Abstract: In recent years, online payment methods have been used widely as an outcome of the rapid increase in non-cash and digital electronic transactions. Credit cards represent one of the electronic payment methods. With the advancement of online payments in various products and services, the likelihood of credit card fraud has risen compared to the decades-long history of credit cards. The credit card frauds can be detected by evaluating the credit card purchasing patterns using the historical data in order to detect the frauds. This data evaluation can help the banks or other organizations offering credit cards to minimize their losses due to the credit card frauds. The historical data evaluation with the current purchasing patterns requires statistical modeling, which can automatically evaluate the fraudulent patterns and alarm the banks about the transactions. This helps the banks for early detection of the frauds, where they can easily eliminate the credit card frauds by declining the suspected transactions. And also blockchain technology is applied to prevent the hacker to view customers details so that fraudsters can't use stolen credit card information to open new accounts, obtain loans, and engage in other illegal activities. Credit card fraud detection and prevention have become essential for banks and other financial institutions to safeguard their customers' financial transactions. This paper presents an overview of credit card fraud detection and prevention techniques.