Search

Copyright of Contemporary Accounting Research is the property of Canadian Academic Accounting Association and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Since the mid-1980s it has been known that Byzantine Agreement can be solved with probability 1 asynchronously, even against an omniscient, computationally unbounded adversary that can adaptively corrupt up to f < n/3 parties. Moreover, the problem is insoluble with f ≥ n/3 corruptions. However, Bracha's [13] 1984 protocol (see also Ben-Or [8]) achieved f < n/3 resilience at the cost of exponential expected latency 2Θ (n), a bound that has never been improved in this model with f = ⌊ (n-1)/3 ⌋ corruptions. In this article, we prove that Byzantine Agreement in the asynchronous, full information model can be solved with probability 1 against an adaptive adversary that can corrupt f < n/3 parties, while incurring only polynomial latency with high probability. Our protocol follows an earlier polynomial latency protocol of King and Saia [33, 34], which had suboptimal resilience, namely f ≈ n/109 [33, 34]. Resilience f = (n-1)/3 is uniquely difficult, as this is the point at which the influence of the Byzantine and honest players are of roughly equal strength. The core technical problem we solve is to design a collective coin-flipping protocol that eventually lets us flip a coin with an unambiguous outcome. In the beginning, the influence of the Byzantine players is too powerful to overcome, and they can essentially fix the coin's behavior at will. We guarantee that after just a polynomial number of executions of the coin-flipping protocol, either (a) the Byzantine players fail to fix the behavior of the coin (thereby ending the game) or (b) we can "blacklist" players such that the blacklisting rate for Byzantine players is at least as large as the blacklisting rate for good players. The blacklisting criterion is based on a simple statistical test of fraud detection. [ABSTRACT FROM AUTHOR]

The monitoring and early warning of financial risks have become a crucial link in maintaining market stability and safeguarding the rights and interests of investors. Traditional financial risk monitoring methods often rely on a single data source or analysis model, making it challenging to comprehensively and accurately capture risk signals. Therefore, this paper proposes a novel financial risk monitoring model based on multimodal neural networks, which innovatively integrates multiple data sources, such as vision, language and audio, and utilizes their inherent correlations to enhance the accuracy of risk identification. First, by employing the Bidirectional Long Short-Term Memory Network (BiLSTM) structure and incorporating the self-attention mechanism, the semantic information of financial texts is deeply analyzed through the calculation of dynamic weight coefficients. Additionally, Option-based Hierarchical Reinforcement Learning (OHRL) is utilized to accurately model the behavior of market participants, capturing nuanced changes in their decision-making process. By integrating these two types of information, a comprehensive BiLSTM-OHRL model is formulated to evaluate the risk status of financial markets in a more comprehensive and accurate manner. The results demonstrate that the model performs impressively in financial risk monitoring, accurately capturing the emotional and behavioral characteristics of market participants, thereby enhancing the comprehensiveness and predictive capability of the monitoring model. It provides robust technical support for the stable operation of the financial market. [ABSTRACT FROM AUTHOR]

In Federated Learning, Anomaly Detection poses significant challenges due to the decentralized nature of data, especially under Non-IID distributions. This study proposes a federated threshold calculation method that aggregates summary statistics from normal and anomalous data across clients to create a global threshold for Anomaly Detection with federated Autoencoders, enhancing detection accuracy and robustness while ensuring privacy. Extensive experiments on datasets, including Credit Card Fraud Detection, Shuttle, and Covertype, show that our approach consistently outperforms existing federated and local threshold calculation methods. These findings highlight the potential of summary statistics in improving federated Anomaly Detection under Non-IID conditions. [ABSTRACT FROM AUTHOR]

Although activist short sellers can play a crucial role in fraud detection, they have come under scrutiny following accusations of systematically disseminating false negative information. We develop a framework delineating the roles of campaign-specific private information quality and short-selling dynamics in shaping disclosure incentives. We predict that the act of disclosure combined with pre-disclosure stock lending dynamics is informative about the quality of an activist's private information. We find that increased pre-disclosure shorting intensity is associated with more negative post-disclosure returns, adverse media coverage, and consequential campaign outcomes, including auditor turnover, accounting restatements, class-action lawsuits, and performance-related delistings. Furthermore, elevated short-selling costs and risks magnify the association between pre-disclosure shorting intensity and post-disclosure underperformance. Finally, we examine V-shaped reversals and short covering following activists' disclosures and find no evidence of systematic manipulation. We conclude that activists disclosing fraud allegations under their own names are discouraged from engaging in "short-and-distort" schemes. Data Availability: Data are available from the sources cited in the text. JEL Classifications: G12; G14; G23; M41. [ABSTRACT FROM AUTHOR]

Financial institutions and businesses face an ongoing challenge from fraudulent transactions, prompting the need for effective detection methods. Detecting credit card fraud is crucial for identifying and preventing unauthorized transactions. While credit card fraud incidents are relatively rare, they can result in substantial financial losses, particularly due to the high monetary value associated with fraudulent transactions. Timely detection of fraud enables investigators to take swift actions to mitigate further losses. However, the investigation process is often time-consuming, limiting the number of alerts that can be thoroughly examined each day. Therefore, the primary objective of a fraud detection model is to provide accurate alerts while minimizing false alarms and missed fraud cases. In this paper, we introduce a state-of-the-art hybrid ensemble (ENS) dependable machine learning (ML) model that intelligently combines multiple algorithms with proper weighted optimization using grid search, including decision tree (DT), random forest (RF), K-nearest neighbor (KNN), and multilayer perceptron (MLP), to enhance fraud identification. To address the data imbalance issue, we employ the instant hardness threshold (IHT) technique in conjunction with logistic regression (LR), surpassing conventional approaches. Our experiments are conducted on a publicly available credit card dataset comprising 284,807 transactions. The proposed model achieves impressive accuracy rates of 99.66%, 99.73%, 98.56%, and 99.79%, and a perfect 100% for the DT, RF, KNN, MLP and ENS models, respectively. The hybrid ensemble model outperforms existing works, establishing a new benchmark for detecting fraudulent transactions in high-frequency scenarios. The results highlight the effectiveness and reliability of our approach, demonstrating superior performance metrics and showcasing its exceptional potential for real-world fraud detection applications. [ABSTRACT FROM AUTHOR]

For financial institutions, credit card fraud detection is a critical activity where the accuracy and efficiency of detection models are important. Traditional methods often use standard feature selection techniques that may ignore refined patterns in transaction data. This paper presents a new approach that combines feature aggregation with Exhaustive Feature Selection (EFS) to enhance the performance of credit card fraud detection models. Through feature aggregation, higher-order characteristics are created to capture complex relationships within the data, then find the most relevant features by evaluating all possible subsets of features systemically using EFS. Our method was tested using a public credit card fraud dataset, PaySim. Four popular learning classifiers—random forest (RF), decision tree (DT), logistic regression (LR), and deep neural network (DNN)—are used with balanced datasets to evaluate the techniques. The findings show a large improvement in detection accuracy, F1 score, and AUPRC compared to other approaches. Specifically, our method had improved F1 score, precision, and recall measures, which underlines its ability to handle fraudulent transactions' nuances more effectively as compared to other approaches. This article provides an overall analysis of this method's impact on model performance, giving some insights for future studies regarding fraud detection and related fields. [ABSTRACT FROM AUTHOR]

Background and Aim: Adulteration, or the inclusion of meats not declared on the label of processed meat products, constitutes a fraudulent practice that poses a threat to public health. Sausages, which are processed meats derived from a blend of minced meats that obscure the original muscle's morphological features, are particularly prone to adulteration, making the visual detection of fraud more challenging. The research aimed to detect and measure the proportion of pork, chicken, buffalo, and beef DNA in commercially available processed meat packaged, labeled, and sold as "beef sausages" in Makassar, Indonesia. Materials and Methods: A total of 30 beef sausage samples were collected from traditional and modern markets as well as tourist attractions in Makassar. DNA was isolated and the species were identified using quantitative polymerase chain reaction. Results: The findings revealed that all sausage samples contained not only beef DNA, as indicated on their labels but also undeclared DNA from chicken and buffalo. Notably, pork DNA was not detected in the samples. The frequencies of chicken and buffalo meat were 9.2% and 10%, respectively, whereas it was 0.85% for beef in the beef sausage samples. Conclusion: The discovery of chicken and buffalo species in beef sausage samples indicates adulteration, potentially posing severe quality risks. [ABSTRACT FROM AUTHOR]

Financial fraud detection has been an urgent technical demand in cyberspace. It highly relies on clear extraction and deep representation toward complex relationships inside financial social networks. As consequence, this study combines both knowledge graph and deep learning to deal with such issue. Thus, an intelligent financial fraud detection model based on knowledge graph guidance and deep neural network is proposed in this paper. First, a new knowledge graph based on financially related systems is constructed, which includes multiple entities and relationships. Then, an adversarial learning-based neural network structure is formulated to extract financial attributes. Finally, the detection results can be output according to the extracted factors. Empirically, the proposal is implemented on a real-world dataset for performance evaluation. The experimental results show that it has higher accuracy and effectiveness compared to traditional fraud detection methods. The proposed detection model can not only identify known fraudulent behaviors, but also predict potential fraud patterns based on consumer habits, thereby improving the security and reliability of financial transactions. It can also update the knowledge graph in real-time, enabling it to cope with emerging fraud methods and variants. [ABSTRACT FROM AUTHOR]

Despite several mitigating measures, crime continues to disrupt and destabilise processes and activities in the financial sector. Detective analytics is increasingly explored as an additional mitigative solution by many financial institutions, to respond to the growing crime activities creatively and innovatively. This study aimed to examine how detective analytics can be used to follow the actors of crime activities. Actor-network theory (ANT) is employed as a lens to gain a deeper understanding of how activities can be traced, and tracked, to mitigate financial crime in institutions. The interpretive approach was applied. The findings revealed Seamless integration of incidents, Cybersecurity detection, In-house fraud detection, External infiltrate detection, and Image-matching data into one cohesive system. The study highlights the need for gaining a deeper understanding of networks of actors, following the actors, and passage points within an organisation. The findings have significant implications for improving the efficiency and effectiveness of detective analytics, from both technical and non-technical perspectives. [ABSTRACT FROM AUTHOR]

Fraud detection plays a crucial role in the modern banking sector, aiming to mitigate financial losses affecting both individuals and financial institutions. With a significant portion of the population regularly using credit cards, efforts to enhance financial inclusivity have led to increased card usage. Additionally, the rise of e-commerce has brought about a surge in credit card fraud incidents. Unfortunately, traditional statistical methods used for identifying credit card fraud are time-consuming and may not provide accurate results. As a result, machine learning algorithms have become widely adopted for effective credit card fraud detection. This study addresses the challenge of an imbalanced credit card dataset by employing three sampling strategies: cluster centroid-based majority under-sampling technique (CCMUT), synthetic minority oversampling technique (SMOTE), and oversampling technique. The training dataset is then used to train nine machine learning algorithms, including Random Forest (RF), k nearest neighbors (KNN), Decision Tree (DT), Logistic Regression (LR), Ada-boost, Extra-trees, MLP classifier, Naive Bayes, and Gradient Boosting Classifier. The performance of these approaches is assessed using metrics such as accuracy, precision, recall, f1 score, and f2 score. The dataset used in this study was obtained from the Kaggle data repository. [ABSTRACT FROM AUTHOR]

Fraud detection in banking systems is crucial for financial stability, customer protection, reputation management, and regulatory compliance. Machine Learning (ML) is vital in improving data analysis, real-time fraud detection, and developing fraud techniques by learning from data and adjusting detection strategies accordingly. Feature Selection (FS) is essential for enhancing fraud detection through ML to achieve optimal model accuracy. This is because it helps to eliminate the negative impact of redundant and irrelevant attributes. To enhance the accuracy of the given dataset, the researchers utilized multiple methods to determine the most fitting features. However, it is important to note that when implementing these methods on datasets with larger feature sizes, they may encounter issues with local optimality. Despite this, the researchers continue to work on improving the effectiveness of these methods. This study presents an effective methodology based on the Brown-Bear Optimization (BBO) algorithm to enhance the capacity to accurately identify financial CCF transactions by recognizing pertinent features. BBO has balanced capabilities to reduce dimensionality while enhancing classification accuracy. It is improved by adjusting the positions randomly to enhance exploration and exploitation capabilities, and then it is cloned into a binary variant named Binary BBOA (BBBOA). The Support Vector Machine (SVM), k-nearest Neighbor (k -NN), and Xgb-tree are the ML classifiers used with the suggested methodology. On the Australian credit dataset, the proposed methodology is compared with the basic BBOA and ten current optimizers, such as Binary African Vultures Optimization (BAVO), Binary Salp Swarm Algorithm (BSSA), Binary Atom Search Optimization (BASO), Binary Henry Gas Solubility Optimization (BHGSO), Binary Harris Hawks Optimization (BHHO), Binary Bat Algorithm (BBA), Binary Particle Swarm Optimization (BPSO), Binary Grasshopper Optimization Algorithm (BGOA), and Binary Sailfish Optimizer (BSFO). Regarding Wilcoxon's rank-sum test (α = 0. 05), the superiority and effective consequence of the presented methodology are clear on the utilized dataset and got an accuracy of classification up to 91% in the utilized dataset combined with an attribute reduction length down to 67%. The proposed methodology is further validated using 10 benchmark datasets and outperformed its competitors in most utilized datasets regarding different performance measures. In the end, the proposed methodology is further validated using ten benchmark datasets from the UCI repository. It outperformed its competitors in most of the utilized datasets regarding different performance measures. [ABSTRACT FROM AUTHOR]

Online financial transactions bring convenience to people's lives, but also present vulnerabilities for criminals to embezzle users' accounts and trick users into credit card fraud. Although machine learning methods have been adopted to detect anomalous transactions, it's hard for a single machine learning method to achieve satisfying results with the increasing scale and dimensionality of financial datasets. In addition, for anomaly detection of financial data, there is an obvious imbalance between normal records and abnormal. In this situation, the experimental results cannot be objectively evaluated only by the traditional metrics, such as precision, recall, and accuracy. This paper proposes an AutoEncoder enhanced LightGBM method for credit card detection. The method inherits the advantages of each component, using an AutoEncoder for feature reconstruction on the dataset, and integrating the LightGBM algorithm for improving the GBDT (Gradient Boosting Decison Tree) to detect abnormal data more accurately and efficiently. Besides the traditional evaluation metrics, F-measure, area under curve (AUC), Matthew's correlation coefficient (MCC), and balanced classification rate (BCR) are also adopted as the evaluation metrics. Two financial datasets were used to validate the performance and robustness of the proposed model. Results obtained from the credit card fraud dataset containing 31 features indicate that our model significantly outperforms other models with a recall of 94.85%, representing a 10.70% improvement compared to the best detection performance model with a recall of only 86%. Additionally, our model's BCR score is also significantly better than other models, with a BCR score of 97%, as opposed to the best detection performance model's BCR score of 92%, representing a 5% improvement by our model. Various sampling methods and model combinations were considered in this study. It was found that the SMOTE algorithm combined with the proposed model produced the best results, with an AUC value of 96.83% and an F-measure score of 80.27%. The Santander bank transaction record dataset is a high dimensional large dataset containing 200 features. Experimental results on this dataset reveal that compared to other models, our model significantly improved recall and F-measure results, raising the recall to 94.14% and the F-measure score by 11.51%, surpassing the second-best-performing model. Overall, these findings demonstrate the robustness and superiority of our model in detecting fraudulent transactions and highlight the effectiveness of the SMOTE algorithm in combination with the proposed model. [ABSTRACT FROM AUTHOR]

Credit card fraud detection is a critical challenge in the financial industry, with substantial economic implications. Conventional machine learning (ML) techniques often fail to adapt to evolving fraud patterns and underperform with imbalanced datasets. This study proposes a hybrid deep learning framework that integrates Generative Adversarial Networks (GANs) with Recurrent Neural Networks (RNNs) to enhance fraud detection capabilities. The GAN component generates realistic synthetic fraudulent transactions, addressing data imbalance and enhancing the training set. The discriminator, implemented using various DL architectures, including Simple RNN, Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRUs), is trained to distinguish between real and synthetic transactions and further fine-tuned to classify transactions as fraudulent or legitimate. Experimental results demonstrate significant improvements over traditional methods, with the GAN-GRU model achieving a sensitivity of 0.992 and specificity of 1.000 on the European credit card dataset. This work highlights the potential of GANs combined with deep learning architectures to provide a more effective and adaptable solution for credit card fraud detection. [ABSTRACT FROM AUTHOR]

As one of the supervised learning techniques, classification plays a crucial role in categorizing and predicting the observations across a wide range of machine learning applications such as software defect detection, fraud detection in financial sector, fault and defect detection in manufacturing industry, medical diagnosis, etc. However, most classification algorithms have been developed with the assumption that the class distribution is balanced although unequal class distributions are quite common in many practical cases. When a class imbalance problem exists, in general, the classifier tends to become biased towards the majority class and thus the minority class instances are often misclassified to the majority class. Along with the class imbalance problem, the class overlap is also known as one of the sources that makes the learning task become difficult or sometimes deteriorates the classification performance, especially, when class imbalance problem also exists. Thus, in this research, we propose a cluster impurity-based hybrid resampling method including the partially balanced strategy to improve the classification performance of class imbalanced data with considering intra-cluster class imbalance and inter-cluster overlap problems. Specifically, several clustering methods are employed for identifying the groups (i.e., clusters) of all the instances and the cluster impurity of each instance is computed for measuring the degree of cluster overlap. Then, based on the cluster impurity, the instances are generated and eliminated recursively. To demonstrate the effectiveness of the proposed method, comprehensive experiments are conducted on forty imbalanced datasets and two non-parametric hypothesis tests are employed to show the statistical difference in classification performances between the proposed method and other traditional resampling methods. [ABSTRACT FROM AUTHOR]

This article examines the impact of utilizing generative artificial intelligence optimizations in automating the content generation process. This instance involves the identification of fraudulent content, which is often characterized by dynamic patterns, in addition to content production. The generated contents are constrained, which limits their dimensionality. In this scenario, duplicated contents are eliminated from the automatic creations. Furthermore, the generated ratios are utilized to discover current patterns with minimized losses and errors, hence enhancing the accuracy of generative contents. Furthermore, while analysing the created patterns, we detect a significant discrepancy in lead durations, resulting in the generation of high scores for relevant information. In order to test the results using generative tools, the adversarial network codes are employed in four scenarios. These scenarios involve generating large patterns and reducing the dynamic patterns with an enhanced accuracy of 97% in the projected model. This is in contrast to the existing approach, which only provides a content accuracy of 77% after detecting fraud. [ABSTRACT FROM AUTHOR]

For a long time, decision-making in auditing was limited to a risk-oriented recommendation and consisted of the rigorous analysis of a sample of data. The new trend in the audit decision process focuses on the use of decision support systems (DSSs) founded on data analytics (DA) to better concentrate on in-depth analysis. This study examines how DA can improve the audit decision-making approach in the banking sector. We show that DA techniques can improve the quality of audit decision-making within banks and highlight the advantages associated with mastering these techniques, which results in a more effective and efficient audit of digital banking transactions. We propose an artifact-based data analytics-driven decision support system (DA-DSS) for an automatic fraud detection system supported by DA. The proposed DA-DSS artifact with a random forest classifier at its core is a promising innovation in the field of electronic transaction fraud detection. The results show that the random forest classifier can accurately classify the data generated by this artifact with an accuracy varying from 88 to 93% using transaction data collected from 2021 to 2022. Other classifiers including k-nearest neighbors (KNN) are also used, with a classification rate ranging from 66 to 88% for the same transaction datasets. These results show that the proposed DA-DSS with random forest can significantly improve auditing by reducing the time required for data analysis and increasing the results' accuracy. Management can use the proposed artifact to enhance and speed up the decision-making process within their organization. [ABSTRACT FROM AUTHOR]

The objective of this paper is to propose a reference point in the phenomenology of poltergeists either for people who want to know more about these phenomena or for researchers looking for cases and sources associated with some particular phenomenon. In parallel, an ongoing work is conducted aimed at building a global case repository of poltergeist cases with their phenomenological characteristics and their sources, which will be available soon at www.macropk.org. A historical view of the 50+ qualitative and quantitative studies of the poltergeist phenomenon is presented along with the different authors/researchers and the publications associated. The different types of phenomena observed are studied from four angles: the physical impacts on the environment, the interactions with people, other features such as duration, focus effect, and contagion, and how the phenomena ended. Each type of event is illustrated through different cases extracted from our case repository (about 1250), often with a short extract from (one of) the sources describing some key characteristics. A discussion about the validity of these data is then developed, looking in particular at testimonials, fraud detection, legal impacts, and the similarity of description of unconnected people. These elements tend to give a strong plausibility to the diverse phenomena observed, even the more "bizarre" ones. Considering all these cases and the details associated with them could help to build a more global picture of the phenomenon. This could provide more ideas based on facts to develop current and new hypotheses, as well as new psychophysical models, in order to make progress in comprehending the phenomenon. A list of the 105 cases used in the description of the phenomenology is provided along with their sources and their distribution across historical periods and geographical areas. [ABSTRACT FROM AUTHOR]

Abnormal behavior recognition is an important technology used to detect and identify activities or events that deviate from normal behavior patterns. It has wide applications in various fields such as network security, financial fraud detection, and video surveillance. In recent years, Deep Convolution Networks (ConvNets) have been widely applied in abnormal behavior recognition algorithms and have achieved significant results. However, existing abnormal behavior detection algorithms mainly focus on improving the accuracy of the algorithms and have not explored the real-time nature of abnormal behavior recognition. This is crucial to quickly identify abnormal behavior in public places and improve urban public safety. Therefore, this paper proposes an abnormal behavior recognition algorithm based on three-dimensional (3D) dense connections. The proposed algorithm uses a multi-instance learning strategy to classify various types of abnormal behaviors, and employs dense connection modules and soft-threshold attention mechanisms to reduce the model's parameter count and enhance network computational efficiency. Finally, redundant information in the sequence is reduced by attention allocation to mitigate its negative impact on recognition results. Experimental verification shows that our method achieves a recognition accuracy of 95.61% on the UCF-crime dataset. Comparative experiments demonstrate that our model has strong performance in terms of recognition accuracy and speed. [ABSTRACT FROM AUTHOR]

In the realm of credit card fraud detection, the landscape is continually evolving, demanding innovative approaches to stay ahead of increasingly sophisticated fraudulent activities. Our research pioneers a groundbreaking methodology that amalgamates the power of bipartite graph visualization with advanced machine learning techniques. This fusion yields a comprehensive framework capable of effectively evaluating the efficacy of a random forest classifier in uncovering fraudulent credit card transactions. Our study showcases the compelling application of this methodology, offering a paradigm shift in how we analyze and understand credit card fraud detection systems. By seamlessly integrating machine learning algorithms with network analysis, we provide a holistic view of the data, unveiling intricate patterns hidden within. At the heart of our approach lies the innovative use of bipartite graphs, which serve as a dynamic visual bridge between model predictions and real-world outcomes. This visual representation not only enhances interpretability but also facilitates a deeper understanding of the classifier’s performance. By visually mapping the relationships between transactions and their respective classifications, our methodology offers actionable insights into both successful detection and potential areas for improvement. Empowering analysts and stakeholders, our approach facilitates informed decisionmaking by enabling them to fine-tune model parameters and enhance the overall effectiveness of fraud detection systems. Through this synergy between cutting-edge machine learning and network analysis techniques, we provide a powerful tool to combat the critical challenge of credit card fraud prevention. Step into the future of fraud detection with our innovative methodology, where every transaction is scrutinized with precision, and where security is not just a possibility, but a promise fulfilled. [ABSTRACT FROM AUTHOR]

The most popular payment method in recent years is the credit card. Due to the E-commerce industry’s explosive growth, the usage of credit cards for online purchases have been greatly increased as a result frauds has increased. Banks have been facing challenges to detect the credit card system fraud in recent years. Credit card fraud happens when the card was stolen for any unauthorized purposes or if the fraudster utilizes the credit card information for his own use. In order to prevent credit card fraud, it is essential to build detection measures. While detecting credit card theft with machine learning (ML), the features of credit card frauds play an important and they must be carefully selected. A fraud detection algorithm must be created in order to correctly locate and stop fraudulent activity as technology advances along with the amount of fraud cases. ML methods are essential for identifying fraudulent transactions. The implementation of fraud detection models is particularly difficult because of the sensitive nature of the data, the unbalanced class distributions, and the lack of data. In this work, an intelligent approach to detect and predict online fraud transaction using extreme gradient boosting (XGBoost) algorithm is described. The XGBoost model predicts whether a transaction is fraud or not. This model will achieve better performance interarm of recall, precision, accuracy and F1-score for credit card fraud detection. [ABSTRACT FROM AUTHOR]

SUMMARY: The scope and complexity of artificial intelligence (AI) applications in auditing have grown beyond automating tasks to performing decision-making tasks. Consequently, understanding how AI-based models arrive at their decisions has become crucial, particularly for auditing tasks that demand greater accountability and that involve complex decision-making processes. In this paper, we explore the implementation of explainable AI (XAI) through a fraud detection use case and demonstrate how integrating an explainability layer using XAI can improve the interpretability of AI models, enabling stakeholders to understand the models' decision-making process. We also present emerging AI regulations in this context. [ABSTRACT FROM AUTHOR]

The financial statement auditor's identification of fraud risk factors, their assessment of fraud risk, and their fraud risk responses are key to the auditor's consideration of fraud and fraud detection. Given that the last review of research related to the search for fraud during the audit occurred nearly a decade ago, we provide a summary of recent academic research to update and inform practitioners, researchers, standard setters, regulators, and other stakeholders in the financial reporting process. We categorize and summarize findings from recent academic studies that focus on the auditor's identification, assessment, and responses to fraud risks. Implications for practice are presented for each of these areas, along with topics and questions for future research. [ABSTRACT FROM AUTHOR]

As e-commerce has grown gradually online item assessments have emerged as a key source of consumer data. That stated, there are problems with the consistency and fictitiousness of the evaluations because there are numerous fake or fraudulent ones. These misleading assessments are generated during the investigation in an attempt to mislead customers about the nature of a real advantage, compromising their ability to make a predetermined decision and damaging the reputations of businesses. A cutting-edge interrogation department revealed that quantum machine learning (QML) could manage a huge amount of machine-trained data and could convey almost emotional choices in the context of inaccurate checks. It is truly beneficial in obtaining reviews for things that are incorrect. Opinion, generating trends, interpersonal relationships, and assessing fatigue is merely a few of the attributes. Tests conducted utilizing the Amazon fraudulent review. The dataset demonstrates that QML tactics outperform conventional knowledge acquisition procedures in errands, including the place of fraudulent reviews. The delicacy and tolerance of incorrect review distinguishing evidence can be significantly advanced, although QML is still in its early stages of development. Both our proposed model and model pass rigorous conventional machine learning algorithms testing with a remarkable level of accuracy. An article introduces a unique approach to fraudulent review detection and brings in the QNN algorithm as a solution. A deep learning model, such as this one, has an 86% accuracy rate in quantum computer implementation, which is an impressive level of innovation, especially if it comes with successful results. Involvement in these cutting-edge technologies promises significant benefits in battling the problem of false identities on the Web. In our case, the experimental results demonstrate that our QNN algorithm, which can accurately identify fake reviews, will become a key weapon for suppressing various forms of fraudulence on emerging digital technology platforms. [ABSTRACT FROM AUTHOR]

Consider a finite directed graph without cycles in which the arrows are weighted by positive weights. We present an algorithm for the computation of a new distance, called path-length-weighted distance, which has proven useful for graph analysis in the context of fraud detection. The idea is that the new distance explicitly takes into account the size of the paths in the calculations. It has the distinct characteristic that, when calculated along the same path, it may result in a shorter distance between far-apart vertices than between adjacent ones. This property can be particularly useful for modeling scenarios where the connections between vertices are obscured by numerous intermediate vertices, such as in cases of financial fraud. For example, to hide dirty money from financial authorities, fraudsters often use multiple institutions, banks, and intermediaries between the source of the money and its final recipient. Our distance would serve to make such situations explicit. Thus, although our algorithm is based on arguments similar to those at work for the Bellman–Ford and Dijkstra methods, it is in fact essentially different, since the calculation formula contains a weight that explicitly depends on the number of intermediate vertices. This fact totally conditions the algorithm, because longer paths could provide shorter distances—contrary to the classical algorithms mentioned above. We lay out the appropriate framework for its computation, showing the constraints and requirements for its use, along with some illustrative examples. [ABSTRACT FROM AUTHOR]

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Credit card fraud detection is a critical issue for financial institutions due to significant financial losses and the erosion of customer trust. Fraud not only impacts the bottom line but also undermines the confidence customers place in financial services, leading to long-term reputational damage. Traditional machine learning methods struggle to improve detection accuracy with limited data, adapt to new fraud techniques, and detect complex fraud patterns. To address these challenges, we present FedGAT-DCNN, a model integrating a Graph Attention Network (GAT) and dilated convolutions within a federated learning framework. FedGAT-DCNN employs federated learning, allowing financial institutions to collaboratively train models using local datasets, enhancing accuracy and robustness while maintaining data privacy. Incorporating a GAT enables continuous model updates across institutions, quickly adapting to new fraud patterns. Dilated convolutions extend the model's receptive field without extra computational overhead, improving detection of subtle and complex fraudulent activities. Experiments on the 2018CN and 2023EU datasets show that FedGAT-DCNN outperforms traditional models and other federated learning methods, achieving a ROC-AUC of 0.9712 on the 2018CN dataset and 0.9992 on the 2023EU dataset. These results highlight FedGAT-DCNN's robustness, accuracy, and applicability in real-world fraud detection scenarios. [ABSTRACT FROM AUTHOR]

In the cybersecurity industry, where legitimate transactions far outnumber fraudulent ones, detecting fraud is of paramount significance. In order to evaluate the accuracy of detecting fraudulent transactions in imbalanced real datasets, this study compares the efficacy of two approaches, random under-sampling and oversampling, using the synthetic minority over-sampling technique (SMOTE). Random under-sampling aims for fairness by excluding examples from the majority class, but this compromises precision in favor of recall. To strike a balance and ensure statistical significance, SMOTE was used instead to produce artificial examples of the minority class. Based on the data obtained, it is clear that random under-sampling achieves high recall (92.86%) at the expense of low precision, whereas SMOTE achieves a higher accuracy (86.75%) and a more even F1 score (73.47%) at the expense of a slightly lower recall. As true fraudulent transactions require at least two methods for verification, we investigated different machine learning methods and made suitable balances between accuracy, F1 score, and recall. Our comparison sheds light on the subtleties and ramifications of each approach, allowing professionals in the field of cybersecurity to better choose the approach that best meets the needs of their own firm. This research highlights the need to resolve class imbalances for effective fraud detection in cybersecurity, as well as the need for constant monitoring and the investigation of new approaches to increase applicability. [ABSTRACT FROM AUTHOR]

Crowdfunding platforms are important for startups, since they offer diverse financing options, market validation, and promotional opportunities through an investor community. These platforms provide detailed company information, aiding informed investment decisions within a regulated and secure environment. Machine learning (ML) techniques are important in analyzing large data sets, detecting anomalies and fraud, and enhancing decision-making and business strategies. A systematic review employed PRISMA guidelines, which studied how ML improves fraud detection on digital crowdfunding platforms. The analysis includes English-language studies from peer-reviewed journals published between 2018 and 2023 to analyze the pre- and post-COVID-19 pandemic. The findings indicate that ML techniques such as Random Forest, Support Vector Machine, and Artificial Neural Networks significantly enhance the predictive accuracy and utility of tax planning for startups considering equity crowdfunding. The United States, Germany, Canada, Italy, and Turkey do not present statistically significant differences at the 95% confidence level, standing out for their notable academic visibility. Florida Atlantic and Cornell Universities, Springer and John Wiley & Sons Ltd. publishing houses, and the Journal of Business Ethics and Management Science magazines present the highest citations without statistical differences at the 95% confidence level. [ABSTRACT FROM AUTHOR]

We examine the impact of corporate governance and personal networks on corporate fraud in Japanese companies, using panel logit and Cox proportional hazard models to analyze fraud occurrence and detection. This study focuses on the effects of Japan's recent corporate governance reform and explores the unique influence of personal networks. Our key findings indicate that recent changes in corporate governance in Japan have been effective in preventing the occurrence of fraud and accelerating its detection. Additionally, stronger personal networks among board members help prevent fraud concealment, highlighting cultural differences in the effectiveness of personal networks in corporate governance compared to findings from Europe and the US. [ABSTRACT FROM AUTHOR]

Detecting fraudulent activities in credit card transactions can be challenging due to issues like high dimensionality and class imbalance that are often present in the datasets. To address these challenges, data reduction techniques such as data sampling and feature selection have become essential. In this study, we compare four approaches for data reduction: using data sampling alone, employing feature selection alone, applying data sampling followed by feature selection, and using feature selection followed by data sampling. Additionally, we include results using all features. We build classification models using five Decision Tree-based classifiers and Logistic Regression, and evaluate their performance using two performance metrics: the Area Under the Receiver Operating Characteristic Curve (AUC) and the Area under the Precision–Recall Curve (AUPRC). In this work, we adopt ensemble supervised feature selection (SFS) techniques and Random Undersampling (RUS) for data reduction. The experimental results demonstrate that all four data reduction techniques have the potential to improve the performance of classifiers. These results are valuable since the classifiers available are dependent upon application domains, computing environments, and licensing agreements. However, these techniques can be applied independently of all these dependencies. We recommend utilizing the ensemble SFS followed by RUS (SFS–RUS) approach as the preferred data reduction method due to its ability to run feature selection and data sampling in parallel. Additionally, we find that XGBoost and CatBoost outperform other classifiers. [ABSTRACT FROM AUTHOR]

The rapid advancement of the Internet and digital payments has transformed the landscape of financial transactions, leading to both technological progress and an alarming rise in cybercrime. This study addresses the critical issue of financial fraud detection in the era of digital payments, focusing on enhancing operational risk frameworks to mitigate the increasing threats. The objective is to improve the predictive performance of fraud detection systems using machine learning techniques. The methodology involves a comprehensive data preprocessing and model creation process, including one‐hot encoding, feature selection, sampling, standardization, and tokenization. Six machine learning models are employed for fraud detection, and their hyperparameters are optimized. Evaluation metrics such as accuracy, precision, recall, and F1‐score are used to assess model performance. Results reveal that XGBoost and Random Forest outperform other models, achieving a balance between false positives and false negatives. The study meets the requirements for fraud detection systems, ensuring accuracy, scalability, adaptability, and explainability. This paper provides valuable insights into the efficacy of machine learning models for financial fraud detection and emphasizes the importance of striking a balance between false positives and false negatives. [ABSTRACT FROM AUTHOR]

From the various perspectives of machine learning (ML) and the multiple models used in this discipline, there is an approach aimed at training models for the early detection (ED) of anomalies. The early detection of anomalies is crucial in multiple areas of knowledge since identifying and classifying them allows for early decision making and provides a better response to mitigate the negative effects caused by late detection in any system. This article presents a literature review to examine which machine learning models (MLMs) operate with a focus on ED in a multidisciplinary manner and, specifically, how these models work in the field of fraud detection. A variety of models were found, including Logistic Regression (LR), Support Vector Machines (SVMs), decision trees (DTs), Random Forests (RFs), naive Bayesian classifier (NB), K-Nearest Neighbors (KNNs), artificial neural networks (ANNs), and Extreme Gradient Boosting (XGB), among others. It was identified that MLMs operate as isolated models, categorized in this article as Single Base Models (SBMs) and Stacking Ensemble Models (SEMs). It was identified that MLMs for ED in multiple areas under SBMs' and SEMs' implementation achieved accuracies greater than 80% and 90%, respectively. In fraud detection, accuracies greater than 90% were reported by the authors. The article concludes that MLMs for ED in multiple applications, including fraud, offer a viable way to identify and classify anomalies robustly, with a high degree of accuracy and precision. MLMs for ED in fraud are useful as they can quickly process large amounts of data to detect and classify suspicious transactions or activities, helping to prevent financial losses. [ABSTRACT FROM AUTHOR]

Fraud seriously threatens individual interests and social stability, so fraud detection has attracted much attention in recent years. In scenarios such as social media, fraudsters typically hide among numerous benign users, constituting only a small minority and often forming "small gangs". Due to the scarcity of fraudsters, the conventional graph neural network might overlook or obscure critical fraud information, leading to insufficient representation of fraud characteristics. To address these issues, the tran-smote on graphs (GTS) method for fraud detection is proposed by this study. Structural features of each type of node are deeply mined using a subgraph neural network extractor, these features are integrated with attribute features using transformer technology, and the node's information representation is enriched, thereby addressing the issue of inadequate feature representation. Additionally, this approach involves setting a feature embedding space to generate new nodes representing minority classes, and an edge generator is used to provide relevant connection information for these new nodes, alleviating the class imbalance problem. The results from experiments on two real datasets demonstrate that the proposed GTS, performs better than the current state-of-the-art baseline. [ABSTRACT FROM AUTHOR]

This study addresses the critical challenge of data imbalance in credit card fraud detection (CCFD), a significant impediment to accurate and reliable fraud prediction models. Fraud detection (FD) is a complex problem due to the constantly evolving tactics of fraudsters and the rarity of fraudulent transactions compared to legitimate ones. Efficiently detecting fraud is crucial to minimize financial losses and ensure secure transactions. By developing a framework that transitions from imbalanced to balanced data, the research enhances the performance and reliability of FD mechanisms. The strategic application of Meta-heuristic optimization (MHO) techniques was accomplished by analyzing a dataset from Kaggle's CCF benchmark datasets, which included data from European credit-cardholders. They evaluated their capability to pinpoint the smallest, most relevant set of features, analyzing their impact on prediction accuracy, fitness values, number of selected features, and computational time. The study evaluates the effectiveness of 15 MHO techniques, utilizing 9 transfer functions (TFs) that identify the most relevant subset of features for fraud prediction. Two machine learning (ML) classifiers, random forest (RF) and support vector machine (SVM), are used to evaluate the impact of the chosen features on predictive accuracy. The result indicated a substantial improvement in model efficiency, achieving a classification accuracy of up to 97% and reducing the feature size by up to 90%. In addition, it underscored the critical role of feature selection in optimizing fraud detection systems (FDSs) and adapting to the challenges posed by data imbalance. Additionally, this research highlights how machine learning continues to evolve, revolutionizing FDSs with innovative solutions that deliver significantly enhanced capabilities. [ABSTRACT FROM AUTHOR]

Financial fraud is a serious challenge in a rapidly evolving digital economy that places increasing demands on detection systems. However, traditional methods are often limited by the dimensional information of the corporations themselves and are insufficient to deal with the complexity and dynamics of modern financial fraud. This study introduces a novel intelligent financial fraud detection support system, leveraging a three-level relationship penetration (3-LRP) method to decode complex fraudulent networks and enhance prediction accuracy, by integrating the fuzzy rough density-based feature selection (FRDFS) methodology, which optimizes feature screening in noisy financial environments, together with the fuzzy deterministic soft voting (FDSV) method that combines transformer-based deep tabular networks with conventional machine learning classifiers. The integration of FRDFS optimizes feature selection, significantly improving the system's reliability and performance. An empirical analysis, using a real financial dataset from Chinese small and medium-sized enterprises (SMEs), demonstrates the effectiveness of our proposed method. This research enriches the financial fraud detection literature and provides practical insights for risk management professionals, introducing a comprehensive framework for early warning and proactive risk management in digital finance. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Fraudulent credit card transactions impact both consumers and card issuers. The ability to detect fraudulent credit card transactions can reduce the cost of credit card use. Prior research has shown that machine learning and ensemble models can identify fraudulent transactions with good accuracy. However, no study has been found that compares heterogeneous and homogeneous models. This research study examines and compares machine learning algorithms with multiple ensemble models for detecting fraudulent credit card transactions using data available from a U.S.-based credit card issuer. The results show that heterogeneous ensemble models can better detect fraudulent and non-fraudulent transactions than individual and homogeneous models. The results suggest that underlying individual algorithms are used in the ensemble matter. Specifically, heterogeneous models that use both random forest modeling and neural network modeling tend to outperform individual models and ensemble models that do not utilize both. [ABSTRACT FROM AUTHOR]

This paper addresses the critical challenge of fraud detection in medical insurance claims, a pervasive issue causing significant financial losses in healthcare. The primary goal is to develop an advanced fraud detection approach by integrating multiple unsupervised machines learning algorithms, leveraging their collective strengths through a majority voting mechanism, where labelling of data is unavailable. Central to this approach is the ensemble of 18 novel unsupervised algorithms, specifically, anomaly detection models. The novelty lies in the majority voting system employed to aggregate the decisions from these diverse algorithms, enhancing the reliability and accuracy of fraud detection. To validate the effectiveness of the proposed system, a dual approach is employed. Firstly, human experts in the medical insurance field review a subset of claims to establish a benchmark for the model's performance. Secondly, the system's effectiveness is quantitatively assessed using key statistical metrics. The system utilizes real-world insurance claim data to ensure quality and relevance, where the two datasets were collected from countries in the Gulf region. The findings reveal significant improvement in fraud detection at various activity levels; from doctor, provider, and patient, where the patient model reached 79 % precision. The system not only aligns well with human expert judgments but also demonstrates superior performance on the specified statistical metrics, indicating effective clustering and anomaly detection. Some real use cases were captured by the model and deeply investigated by human experts, which demonstrated advantages by the proposed approach in detecting fraud at multiple levels, of providers, doctors, and patients. [ABSTRACT FROM AUTHOR]

Research on DeepFake detection using deep neural networks (DNNs) has gained more attention in an effort to detect and categorize DeepFakes. In essence, DeepFakes are regenerated content made by changing particular DNN model elements. In this study, a summary of DeepFake detection methods for images and videos involving faces will be given based on their effectiveness, outcomes, methodology, and type of detection method. We will analyze and categorize the many DeepFake-generating techniques now in use into five primary classes. DeepFake datasets are frequently used to train and test DeepFake models. We will also cover the latest developments in DeepFake dataset trends that are currently accessible. We will also examine the problems in building a generalized DeepFake detection model. Lastly, the difficulties in creating and identifying DeepFakes will be covered. [ABSTRACT FROM AUTHOR]

Tea is central to the culture and economy of the Middle East countries, especially in Iran. At some levels of society, it has become one of the main food items consumed by households. Bioactive compounds in tea, known for their antioxidant and anti-inflammatory properties, have proven to confer neuroprotective effects, potentially mitigating diseases such as Parkinson's, Alzheimer's, and depression. However, the popularity of black tea has also made it a target for fraud, including the mixing of genuine tea with foreign substitutes, expired batches, or lower quality leaves to boost profits. This paper presents a novel approach to identifying counterfeit Iranian black tea and quantifying adulteration with tea waste. We employed five deep learning classifiers—RegNetY, MobileNet V3, EfficientNet V2, ShuffleNet V2, and Swin V2T—to analyze tea samples categorized into four classes, ranging from pure tea to 100% waste. The classifiers, tested in both patched and non-patched formats, achieved high accuracy, with the patched MobileNet V3 model reaching an accuracy of 95% and the non-patched EfficientNet V2 model achieving 90.6%. These results demonstrate the potential of image processing and deep learning techniques in combating tea fraud and ensuring product integrity in the tea industry. [ABSTRACT FROM AUTHOR]

This research deals with the critical issue of credit card fraud, a problem that has escalated in the last decade due to the significant increase in credit card usage, largely driven by advances in international trade, e-commerce, and FinTech. With global losses projected to exceed USD 400 billion in the next decade, the urgent need for effective fraud detection systems is apparent. Our study leverages the power of machine learning (ML) and presents a novel approach to credit card fraud detection. We used the European cardholders dataset for model training, addressing the data imbalance issue that often hinders the effectiveness of the learning process. As a key innovative element, we introduce compact data learning (CDL), a powerful tool for reducing the size and complexity of the training dataset without sacrificing the accuracy of the ML system. Comparative experiments have shown that our CDL-adapted feature reduction outperforms various ML algorithms and feature reduction methods. The findings of this research not only contribute to the theoretical foundations of fraud detection but also provide practical implications for the financial sector, which can benefit immensely from the enhanced fraud detection system. [ABSTRACT FROM AUTHOR]

With the rapid development of Internet finance, the problem of financial fraud has become increasingly prominent, which has brought severe challenges to the security and stability of the financial industry. This paper aims to use artificial intelligence (AI) technology to empower data mining models to build an efficient financial fraud detection and prevention system. First of all, through the analysis of the development trend of Internet finance and the current situation of financial fraud, the limitations of traditional prevention and control measures in the face of big data and complex fraud modes are revealed. Secondly, the paper introduces the application prospect of AI technology in the financial field, especially the advantages and potential in data mining and fraud detection. Then, the data mining techniques adopted are discussed in detail, including the application of machine learning-based model recognition and artificial intelligence algorithms, as well as data preprocessing and feature engineering in big data environment. Further, the paper describes the system architecture design and key technology implementation, including model training and optimization, real-time monitoring and early warning solutions. Finally, through the in-depth analysis and evaluation of the experimental results, the paper verifies the remarkable effect and feasibility of the system in financial fraud detection and prevention, and provides a new technical guarantee and risk management strategy for the financial industry. The experimental results show that the model has achieved good results in the actual data in the financial field, and provides effective technical guarantee and support for financial security. [ABSTRACT FROM AUTHOR]

The current model of healthcare insurance claim adjudication faces significant challenges, in particular fraudulent claims which significantly strain the economy. This paper introduces a novel approach that integrates Data Aggregation, Artificial Intelligence (AI), and Blockchain technologies to enhance the efficiency of healthcare claim adjudication. We present in this study an initial framework that integrates an AI-enhanced smart contract at the data aggregation level. A new concept that enhances the existing smart contract models commonly discussed in blockchain-related insurance literature. Our primary goal is to improve fraud detection and maximize the use of extensive data generated within the insurance ecosystem for prediction, learning, and strategic planning. The concept of an AI-data aggregation-level smart contract, introduced here, holds promise for broad application across various blockchain platforms, not limited to our discussion on healthcare claims insurance adjudication. [ABSTRACT FROM AUTHOR]

Spiking neural membrane systems (or spiking neural P systems, SNP systems) are a new type of computation model which have attracted the attention of plentiful scholars for parallelism, time encoding, interpretability and extensibility. The original SNP systems only consider the time delay caused by the execution of rules within neurons, but not caused by the transmission of spikes via synapses between neurons and its adaptive adjustment. In view of the importance of time delay for SNP systems, which are a time encoding computation model, this study proposes SNP systems with adaptive synaptic time delay (ADSNP systems) based on the dynamic regulation mechanism of synaptic transmission delay in neural systems. In ADSNP systems, besides neurons, astrocytes that can generate adenosine triphosphate (ATP) are introduced. After receiving spikes, astrocytes convert spikes into ATP and send ATP to the synapses controlled by them to change the synaptic time delays. The Turing universality of ADSNP systems in number generating and accepting modes is proved. In addition, a small universal ADSNP system using 93 neurons and astrocytes is given. The superiority of the ADSNP system is demonstrated by comparison with the six variants. Finally, an ADSNP system is constructed for credit card fraud detection, which verifies the feasibility of the ADSNP system for solving real-world problems. By considering the adaptive synaptic delay, ADSNP systems better restore the process of information transmission in biological neural networks, and enhance the adaptability of SNP systems, making the control of time more accurate. [ABSTRACT FROM AUTHOR]

Cost‐sensitive ensemble learning as a combination of two approaches, ensemble learning and cost‐sensitive learning, enables generation of cost‐sensitive tree‐based ensemble models using the cost‐sensitive decision tree (CSDT) learning algorithm. In general, tree‐based models characterize nice graphical representation that can explain a model's decision‐making process. However, the depth of the tree and the number of base models in the ensemble can be a limiting factor in comprehending the model's decision for each sample. The CSDT models are widely used in finance (e.g., credit scoring and fraud detection) but lack effective explanation methods. We previously addressed this gap with cost‐sensitive tree Shapley Additive Explanation Method (CSTreeSHAP), a cost‐sensitive tree explanation method for the single‐tree CSDT model. Here, we extend the introduced methodology to cost‐sensitive ensemble models, particularly cost‐sensitive random forest models. The paper details the theoretical foundation and implementation details of CSTreeSHAP for both single CSDT and ensemble models. The usefulness of the proposed method is demonstrated by providing explanations for single and ensemble CSDT models trained on well‐known benchmark credit scoring datasets. Finally, we apply our methodology and analyze the stability of explanations for those models compared to the cost‐insensitive tree‐based models. Our analysis reveals statistically significant differences between SHAP values despite seemingly similar global feature importance plots of the models. This highlights the value of our methodology as a comprehensive tool for explaining CSDT models. [ABSTRACT FROM AUTHOR]

Financial Technology (FinTech) has sparked widespread interest and is fast spreading. As a result of its continual growth, new terminology in this domain has been introduced. The name 'FinTech' is one such example. This term covers a wide range of practices that are repeatedly used in the financial technology industry. This processes were typically accomplished in careers or organizations to supply required services through the use of information technology-based applications. The word covers a wide range of delicate subjects, including security, privacy, threats, cyberattacks, and others. Several cutting-edge technologies, including those associated with a mobile embedded system, mobile networks, mobile cloud computing, big data, data analytics techniques, and cloud computing, among others, must be mutually integrated for FinTech to thrive. To be approved by its users, this new technology must overcome serious security and privacy flaws. This research gives a thorough analysis of FinTech by discussing the present as well as expected confidentiality and safety problems facing the financial sector to protect FinTech. Finally, it examines potential obstacles to ensuring financial technology application security and privacy. [ABSTRACT FROM AUTHOR]

Healthcare insurance fraud has become a major problem worldwide in recent decades, resulting in significant financial losses for every affected country. Traditional fraud detection methods, however, often fall short as they primarily focus on analyzing data from the current period, thereby neglecting valuable historical information. In our study, we introduce a novel approach inspired by the financial concept of "credit" to detect fraudulent activities in various domains, such as healthcare insurance, credit card, and online retail transactions. Our approach aims to build a credit evaluation model (CEM) that can distinguish between fraudulent and normal activities by analyzing their historical records. We acknowledge that numerous fraud detection methods have been proposed, but they often struggle to detect edge cases, which limits their practical effectiveness. To address this challenge, our proposed CEM employs a time interval-aware long short-term memory (LSTM) algorithm to assist fraud detection. Furthermore, we propose an innovative approach that transforms traditional binary classification into a multi-classification problem, which improves the model's ability to handle diverse fraudulent activities. We conducted experiments to evaluate the effectiveness of our proposed approach and model, comparing them against baseline algorithms and recently proposed methods. The results indicate that our approach outperforms the others, demonstrating its potential for practical use in detecting fraudulent activities across various domains. [ABSTRACT FROM AUTHOR]

Recognizing fraudulent activity in the banking system is essential due to the significant risks involved. When fraudulent transactions are vastly outnumbered by non-fraudulent ones, dealing with imbalanced datasets can be difficult. This study aims to determine the best model for detecting fraud by comparing four commonly used machine learning algorithms: Support Vector Machine (SVM), XGBoost, Decision Tree, and Logistic Regression. Additionally, we utilized the Synthetic Minority Over-sampling Technique (SMOTE) to address the issue of class imbalance. The XGBoost Classifier proved to be the most successful model for fraud detection, with an accuracy of 99.88%. We utilized SHAP and LIME analyses to provide greater clarity into the decision-making process of the XGBoost model and improve overall comprehension. This research shows that the XGBoost Classifier is highly effective in detecting banking fraud on imbalanced datasets, with an impressive accuracy score. The interpretability of the XGBoost Classifier model was further enhanced by applying SHAP and LIME analysis, which shed light on the significant features that contribute to fraud detection. The insights and findings presented here are valuable contributions to the ongoing efforts aimed at developing effective fraud detection systems for the banking industry. [ABSTRACT FROM AUTHOR]

This study aims to improve the accuracy of detecting financial fraud in listed companies by applying various deep learning algorithms. First, we comprehensively reviewed the current state of research on financial fraud theory and identified 67 recognition features to create a new recognition indicator system. Then, we collected data samples of all A-share listed companies from 2010 to 2022, preprocessed them, and generated a basic dataset. To address the unbalanced dataset, we used the Borderline-SMOTE algorithm. Empirical analysis results show that this algorithm can significantly improve the recognition performance of the model. Finally, we conducted experiments on the new dataset using three types of deep learning algorithms. The results show that the model constructed using the Long Short-Term Memory (LSTM) algorithm has the best prediction performance, with an accuracy rate higher than that of the DCRN, autoencoder, and other models. In addition, the classification effects of all deep learning algorithms are better than basic models and ensemble models. This research provides a powerful tool for the regulatory authorities of listed companies, helping them more effectively monitor and prevent financial fraud. We have three innovations in this study: (1) Development of a comprehensive recognition indicator system with 67 features; (2) Utilization of the Borderline-SMOTE algorithm to handle data imbalance; (3) Demonstration of the superior performance of the LSTM algorithm compared to other deep learning, basic, and ensemble models. [ABSTRACT FROM AUTHOR]