To see the other types of publications on this topic, follow the link: Fraud Classification.
Journal articles on the topic 'Fraud Classification'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Fraud Classification.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Nandi, Soumyajit. "Credit Card Fraud Detection Using Random Forest Classification." International Journal for Research in Applied Science and Engineering Technology 11, no. 6 (2023): 2383–90. http://dx.doi.org/10.22214/ijraset.2023.53990.
Full textAbstract:
Abstract: In recent years credit card became one of the essential parts of the people. Sudden increase in E-commerce, customer started using credit card for online purchasing therefore risk of fraud also increases. Instead of carrying a huge amount in hand it is easier to keep credit cards. But nowadays that too becomes unsafe. Nowadays we are facing a big problem on credit card fraud which is increasing in a good percentage. The main purpose is the survey on the various methods applied to detect credit card frauds. From the abnormalities, in the transaction, the fraudulent one is identified. We address this issue in order to implement some machine learning algorithm like random forest, logistic regression in order to detect this kind of fraud. In this paper we increase the efficiency in finding the fraud. However, we discussed and evaluated employee criteria. Currently, the issues of credit card fraud detection have become a big problem for new researchers. We implement an intelligent algorithm which will detect all kind of fraud in a credit card transaction. We handled the problem by finding a pattern of each customer in between fraud and legal transaction. Isolation Forest Algorithm and Local Outlier Factor are used to predict the pattern of transaction for each customer and a decision is made according to them. In order to prevent data from mismatching, all attribute are marked equally.
2
Zaiats, K. D., and D. D. Zaiats. "A new approach to the forensic classification of fraud." Bulletin of Kharkiv National University of Internal Affairs 108, no. 1 (Part 1) (2025): 295–304. https://doi.org/10.32631/v.2025.1.24.
Full textAbstract:
The article substantiates the need to develop a methodology for investigating fraud based on the forensic classification of these criminal offences. It is advisable to choose the criteria for classification of a particular type or group of crimes from the point of view of the practical significance of the differentiation made. Such a criterion ensures grouping of manifestations of crimes based on common features of the mechanism of commission, which, in turn, affects the formation of typical investigative situations of the initial and subsequent stages of investigation, tactical tasks and their solution by appropriate means. The analysis of works by forensic scientists and criminologists who propose to divide frauds into groups depending on the field of activity in which they are committed is made. It is determined that the methodology for investigating fraud developed on the basis of such a classification will not cover all types of crime, since there are many areas of human activity and each of them may implement fundamentally different schemes of fraudulent activity. Therefore, a different scientific approach to the forensic classification of fraud should be applied. It is noted that the classification should be carried out on the basis of certain elements of the mechanism of committing such criminal offences which significantly affect the formation of investigative situations, tactical tasks of investigation and means of their solution. The article emphasises that it is advisable to classify frauds by such a criterion as the type of legal relations used to implement a fraud scheme for seizing the victim's property or his/her property rights. According to this criterion, criminal offences are classified into: 1) frauds committed under the guise of civil legal relations and domestic transactions; 2) frauds committed under the guise of administrative legal relations; 3) frauds committed under the guise of economic legal relations.
3
Shamila, Bashir Dr. Hamid ur Rehman. "Detecting Mobile Money Laundering Using Genetic Algorithm as Feature Selection Method with Classification Method." LC International Journal of STEM (ISSN: 2708-7123) 1, no. 4 (2021): 121–29. https://doi.org/10.5281/zenodo.5149794.
Full textAbstract:
In recent years, mobile phone payment systems have been extensively used in developed countries. Frauds are affecting the economy of the whole world. Different kinds of mobile money frauds are credit card, bank fraud, insurance fraud and financial fraud. In this paper we discussed financial fraud and proposed an effectiveness method for money laundering. Payment system in fraud divided into four parts, point of sale, mobile payment platform, mobile payment independent and bill payment through mobile. Mobile phones are great source of service for financial transactions. Our objective is to identify the misuse of mobile money transaction and to prevent fraud from financial transaction to save the money. Financial Action Task Force (FATF) is an organization that views internationally money laundering. Financial Action Task Force continuously strengthens its standards for dealing with new risks.The Financial Action Task Force monitors countries to ensure the implementation the Financial Action Task Force Standards and holds countries to account that do not comply. This paper proposes hybrid Genetic algorithm based on feature selection method and investigates the performance of Decision Tree and Boost classification machine learning method. We applied Area under the ROC curve (AUC) and confusion matrix after using the feature selection method. We found the resultsof Decision Tree validation, testing and Boost with different Sampling of both datasets and Boost has better performance than Decision Tree.
4
García, Jesús Enrique, Verónica Andrea González-López, Hugo Helito da Silva, and Thainá Soares Silva. "Risk of fraud classification." 4open 3 (2020): 9. http://dx.doi.org/10.1051/fopen/2020010.
Full textAbstract:
In this article, we define consumers’ profiles of electricity who commit fraud. We also compare these profiles with users’ profiles not classified as fraudsters in order to determine which of these clients should receive an inspection. We present a statistically consistent method to classify clients/users as fraudsters or not, according to the profiles of previously identified fraudsters. We show that it is possible to use several characteristics to inspect the classification of fraud; those aspects are represented by the coding performed in the observed series of clients/users. In this way, several encodings can be used, and the client risk can be constructed to integrate complementary aspects. We show that the classification method has success rates that exceed 77%, which allows us to infer confidence in the methodology.
5
Akinbowale, Oluwatoyin Esther, Mulatu Fekadu Zerihun, and Polly Mashigo. "Towards Mitigating Cyberfraud in the South African Financial Institutions: A Deep Learning Approach." International Journal of Economics and Financial Issues 15, no. 4 (2025): 8–18. https://doi.org/10.32479/ijefi.18685.
Full textAbstract:
This study demonstrates the application of deep learning approach specifically the deep learning for cyberfraud incidence classification and time series prediction in the South African financial institutions. Secondary data from the South African Banking Risk Information Centre (SABRIC) was employed and the data was trained under the deep learning paradigm using the Long Short-Term Memory (LSTM) model and adaptive moment estimation (ADAM) algorithm for fraud incidence classification and time series prediction of fraud incidences. Overall, there were 94.1% correct classifications as opposed to 5.9% incorrect classifications. Moreover, the accuracy, precision, recall and F1-score of the LSTM classification model were 71.668%, 87.5%, 99.1% and 78.78% respectively. This indicates that the developed LSTM model is suitable for classification purposes. In addition, the model’s performance improves as new datasets are fed in. This is evident as the root mean square error (RMSE) reduced from 253.5116 obtained initially to 150.9 after new data was fed in. This study contributes conceptually, theoretically and empirical to knowledge on cyberfraud mitigation. The results show that the LSTM model can be deployed for fraud classification and time series analysis of fraud incidences. The outcome of this study may promote cyber resilience and sustain the fight against the perpetration of cyber-related fraud in South Africa’s financial institutions. The use of the LSTM model for cyberfraud classification and time series prediction of cyberfraud incidences in the South African financial institutions demonstrated in this study is unique.
6
Gupta, Kanika, and Vaishnavi Mall. "COMPARATIVE ANALYSIS OF CLASSIFICATION TECHNIQUES FOR CREDIT CARD FRAUD DETECTION." International Research Journal of Computer Science 9, no. 2 (2022): 9–15. http://dx.doi.org/10.26562/irjcs.2022.v0902.003.
Full textAbstract:
Nowadays, in the global computing environment, online payments are a necessary evil as it makes payment conveniently easier and can be done via an ample of available options like a Credit card, Debit Card, Net Banking, PayPal, Paytm available to make payments easier. The most common mode of payment used in online shopping is Credit Card as it is easier for the customers to directly transfer money from one account to another; without the withdrawal of cash at any point. However, this easy payment mode has opened up paths for multiple frauds which involve theft or illegal tampering of data of the credit card owner. Thus, with the increasing number of fraud cases and losses, it is important to find the best solution to detect credit card fraud as well as minimize the number of frauds in online systems. With the analysis of different sets of research performed on the given problem statement, we have concluded that the issue requires a substantial amount of predictions and application of machine learning to find the accuracy score of those commonly used algorithms to predict which of these three state-of-art-algorithms - Naive Bayes, Logistic Regression and K Neighbours, is best suitable to carry out the research in this area. In order to support our findings, we apply two different approaches i.e. with sampling and without sampling on these algorithms against the same dataset. We claim on the basis of our results that K Neighbours outperformed all in both the approaches and is more suitable to carry forward the fraud detection research using machine learning. The analysis will be useful for those working to derive anti-fraud strategies to predict the fraud patterns and reduce the risk during hefty transactions.
7
Journal, IJSREM. "Secure Scan -Analysis of Credit Card Fraud Detection Using Machine Learning." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, no. 11 (2023): 1–11. http://dx.doi.org/10.55041/ijsrem27368.
Full textAbstract:
Credit Card usage has been drastically increased across the world , now people believe in going cashless and are completely dependent on online transactions .The credit card has made the digital transaction easier and nowadays credit card frauds are drastically increasing in numbers compared to earlier times . A powerful fraud detection system is required to stop these frauds . Fraud detection is the process of monitoring the transaction behaviour of a cardholder to detect whether an incoming transaction is authentic and authorised or not otherwise it will be detected as illicit .Machine learning -based fraud detection systems rely on machine learning algorithms that can be trained with historical data and can perform classification , regression or finding the patterns among the data . Keywords: Credit card machine learning , fraud detection ,historical data, algorithms.
8
Raval, Vasant, and Vivek Raval. "Differentiating risk factors of Ponzi from non-Ponzi frauds." Journal of Financial Crime 26, no. 4 (2019): 993–1005. http://dx.doi.org/10.1108/jfc-07-2018-0075.
Full textAbstract:
Purpose This paper aims to analyze the attributes of Ponzi schemes (“Ponzis”) to determine whether they are a unique class of financial fraud. Design/methodology/approach The authors apply the disposition-based fraud model to classify and differentiate the attributes of Ponzis. This classification exercise helps comprehend the distinct drivers of Ponzis. Findings Fraud risk factors of Ponzis are different from those involved in other financial frauds. Four propositions about risk and risk mitigation measures are developed. Research limitations/implications The research approach used is conceptual, not empirical. However, the insights from this exercise should inform how different Ponzis are from other financial frauds and why they should be treated as a separate class for prevention and enforcement. In turn, this may trigger an interest in empirical research focused on the unique risks of Ponzis. Practical implications Knowledge of risk factors unique to Ponzis will permit a consideration of customized risk mitigation measures to prevent or detect Ponzis. Enforcement actions can also become more effective because of a distinct risk-based classification of Ponzis. Social implications The prevention of damage from Ponzis hinges upon how well prospective victims are educated to become aware of signs of Ponzis. This should lead to the more effective protection of investors from victimization from Ponzi schemes. Originality/value The implicit understanding that all financial frauds are alike and that the risk-factors involved are substantially the same across all classes of fraud is challenged. This revelation opens opportunities to add value through focused research on Ponzis as a distinct class of fraud.
9
Chen, Wei, Amna Saeed Khalifa, Kate L. Morgan, and Ken T. Trotman. "The effect of brainstorming guidelines on individual auditors’ identification of potential frauds." Australian Journal of Management 43, no. 2 (2017): 225–40. http://dx.doi.org/10.1177/0312896217728560.
Full textAbstract:
Revised auditing standards and a focus by regulators on the detection of financial statement fraud have resulted in calls for research to examine alternative forms of fraud brainstorming. We examine the effect of using extended brainstorming guidelines, developed in the psychology literature as part of facilitator training, on auditors’ individual brainstorming performance prior to attending the team brainstorming meeting. We find that these additional brainstorming guidelines help auditors identify a greater quantity and quality of potential frauds. Our findings suggest an easy to implement approach to enhance auditors’ performance in fraud brainstorming. JEL Classification: C91; C92; M42
10
Barakat Saad Ibrahim. "Credit Card Fraud Detection Using Gaussian Mixture Model: A Probabilistic Approach for Enhanced Classification." Journal of Information Systems Engineering and Management 10, no. 49s (2025): 807–18. https://doi.org/10.52783/jisem.v10i49s.9964.
Full textAbstract:
Detection of credit card fraud has lately been considered as a critical task due to the highly imbalanced nature of financial transaction databases. On the other hand, the traditional classification algorithms have been poor at detecting fraudulent activities with an acceptable false-positive range. Hence, this work contributes in a GMM based approach for fraud detection which benefits from GMM probabilistic based classification power for better classification results. The database used in this study is publicly available and was obtained from the Kaggle Credit Card Fraud Detection (CCFD) database. The dataset has 284,807 transactions and only 0.17% of the cases represent fraud. This paper plans to scale the features, train GMM technique with different number of Gaussian components (i.e., 2, 4, 6, 8, and 10), and evaluate their performance with several evaluation metrics. Compared with other traditional classifiers (logistic regression (92.4%), K-nearest neighbors (93.68%), decision tree (88.16%) and support vector machine (94.21%)), the proposed GMM algorithm obtains a highest accuracy of 94.53%. The proposed method, despite of its high accuracy, has limitations under high-dimensional feature dependencies and optimal component selection. From the results obtained over the experimentation process, the GMM proves to be a probable, yet flexible and subservient framework to a complex modelling of probabilities for detection of frauds
11
Mackevičius, Jonas. "The Cycle of Frauds and Conditions Increasing Their Risk." Business: Theory and Practice 13, no. (1) (2012): 50–56. https://doi.org/10.3846/btp.2012.06.
Full textAbstract:
The article presents the analysis of the main stages of fraud life cycle: intension, preparation, implementation, detection or not detection, estimation and prevention. The conditions of fraud appearance are various. The article explores the seven main groups of conditions that increase the fraud risk: 1) organization's leaders competency and their management style; 2) staff and their skill levels; 3) organizational structure of enterprise; 4) financial state of the organization; 5) organization's operations and execution; 6) accounting, auditing and internal control system; 7) external economic factors. This classification helps the leaders of organizations, accountants, internal and external auditors to find frauds easier, explain their reasons and evaluate their influence on business results.
12
Tarjo, Tarjo, and Nurul Herawati. "The Comparison of Two Data Mining Method to Detect Financial Fraud in Indonesia." Accounting and Finance Review (AFR) Vol.2(1) Jan-Mar 2017 2, no. 1 (2017): 01–08. http://dx.doi.org/10.35609/afr.2017.2.1(1).
Full textAbstract:
Objective - This research is expected to improve the weaknesses in the research conducted by Tarjo and Herawati (2015). The objective of this study was to analyse two data mining methods in detecting financial fraud based on Beneish m-score model. Methodology/Technique - The research data were companies who committed fraud based Database Case Sanctions Issuers and Public Companies which was released by the Financial Services Authority in the period 2001-2014. For comparison, researchers also used data from companies that did not commit fraud. Companies were selected based on the same industry group of companies committing fraud for the purposes of classification. Findings - The results show that data mining methods can be used to detect financial fraud based on Beneish m-score model. However, there are differences in the classification. In the logit regression, the results are only limited to the accuracy of classification and weak. While the K-Nearest Neighbor model, in addition, it is capable of performing high classification accuracy. Novelty - The study indicates a better method for detecting financial fraud. Type of Paper Empirical Keywords: Detecting Financial Fraud, Beneish M-Score, Logit Regression, K-Nearest Neighbor. JEL Classification: C81, M41.
13
Sembiring Pelawi, Deni Ekel Ramanda, and Ahmad Saikhu. "DETECTION OF FRAUDULENT ATM TRANSACTIONS USING RULE-BASED CLASSIFICATION TECHNIQUES." JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 10, no. 4 (2025): 961–69. https://doi.org/10.33480/jitk.v10i4.6401.
Full textAbstract:
The significant rise in ATM fraud—reflected in 130,472 suspicious transactions reported in Indonesia in 2022—highlights the urgent need for accurate and efficient real-time fraud detection systems. This study evaluates two complementary detection approaches using a dataset of 20,000 anonymized ATM transactions collected from XYZ Bank between January and December 2022, each labeled by internal fraud analysts as fraud or non-fraud. The models compared are a Rule-Based Classifier and a Decision Tree classifier. The Decision Tree demonstrates strong overall performance, achieving 98% accuracy, 75% precision, 79% recall, and a 77% F1-score, indicating a reliable ability to detect diverse fraud patterns. In contrast, the Rule-Based Classifier yields 60% accuracy, 97% precision, 60% recall, and a 74% F1-score, showing high precision with fewer false alarms but a limited ability to detect varied fraud cases. These results emphasize the trade-off between specificity and sensitivity in static versus adaptive models. To address this, a hybrid detection framework is proposed—combining rule-based screening to filter obvious non-fraud cases, followed by Decision Tree analysis to handle more complex patterns. This approach aims to reduce unnecessary transaction holds and improve detection reliability. This study contributes to the limited comparative research on fraud detection methods using real ATM transaction data within the Indonesian banking context. Future research will focus on adaptive learning models to maintain performance against evolving fraud behaviors in dynamic financial systems.
14
Ermakova, Olga V. "PROBLEMS OF FRAUD CLASSIFICATION IN LENDING." Vestnik Tomskogo gosudarstvennogo universiteta, no. 406 (May 1, 2016): 197–201. http://dx.doi.org/10.17223/15617793/406/30.
Full text
15
Tripathy, Nrusingha, Sidhanta Kumar Balabantaray, Surabi Parida, and Subrat Kumar Nayak. "Cryptocurrency fraud detection through classification techniques." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 3 (2024): 2918. http://dx.doi.org/10.11591/ijece.v14i3.pp2918-2926.
Full textAbstract:
Ethereum and its native cryptocurrency, Ether, have played a worthy attention in the development of the blockchain and cryptocurrency space. Its programmability and smart contract capabilities have made it a foundational platform for decentralized applications and innovations across various industries. Because of its anonymous and decentralized structure, the hotheaded expansion of cryptocurrencies in the payment space has created both enormous potential and concerns related to cybercrime, including money laundering, financing terrorism, illegal and dangerous services. As more financial institutions attempt to integrate cryptocurrencies into their networks, there is an increasing need to create a more transparent network that can withstand these kinds of attacks. In this work, we are using different classification techniques, such as logistic regression (LR), random forest (RF), k-nearest neighbors (KNN), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost) for Ethereum fraud detection. The dataset we are using includes rows of legitimate transactions done using the cryptocurrency Ethereum as well as known fraudulent transactions. The “XGBoost” model, which is noteworthy, detects variations that might attract notice and prevent potential issues in this chore.
16
Tripathy, Nrusingha, Balabantaray Sidhanta Kumar, Surabi Parida, and Subrat Kumar Nayak. "Cryptocurrency fraud detection through classification techniques." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 3 (2024): 2918–26. https://doi.org/10.11591/ijece.v14i3.pp2918-2926.
Full textAbstract:
Ethereum and its native cryptocurrency, Ether, have played a worthy attention in the development of the blockchain and cryptocurrency space. Its programmability and smart contract capabilities have made it a foundational platform for decentralized applications and innovations across various industries. Because of its anonymous and decentralized structure, the hotheaded expansion of cryptocurrencies in the payment space has created both enormous potential and concerns related to cybercrime, including money laundering, financing terrorism, illegal and dangerous services. As more financial institutions attempt to integrate cryptocurrencies into their networks, there is an increasing need to create a more transparent network that can withstand these kinds of attacks. In this work, we are using different classification techniques, such as logistic regression (LR), random forest (RF), k-nearest neighbors (KNN), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost) for Ethereum fraud detection. The dataset we are using includes rows of legitimate transactions done using the cryptocurrency Ethereum as well as known fraudulent transactions. The “XGBoost” model, which is noteworthy, detects variations that might attract notice and prevent potential issues in this chore.
17
Veena, Malik, and C. Dharmadhikari S. "Enriching E-Commerce Fraud Detection by using Machine Learning." International Journal of Recent Technology and Engineering (IJRTE) 9, no. 3 (2020): 140–46. https://doi.org/10.5281/zenodo.5842834.
Full textAbstract:
As there has been a proliferation of the internet platform, it has been increasingly getting affordable for a lot of individuals. The rise has been instrumental in achieving several services including the E-commerce platform. This has led to an unprecedented increase in the amount of fraud that is being committed on this platform. The fraud that is being committed on the E-commerce platforms is very different from the frauds committed on other platforms online. Numerous researches have been performed to combat the evils of credit card frauds and money laundering rings. But there is a severe lack of research on the fraud that is committed on the E-commerce platform. Therefore, this research paper defines an innovative approach for the identification of fraud on E-commerce platforms through the implementation of machine learning approaches. The presented technique utilizes Linear Clustering, Entropy Estimation and Frequent itemset mining in addition to the inclusion of Artificial Neural Networks, Hypergraph formation and Fuzzy classification. The implementation of this system will give more security for E-commerce platform-based transactions by identifying fraudulent activities with better efficiency. The methodology has been tested extensively through rigorous experimentation to evaluate the performance metrics which yielded significantly positive results.
18
Dzobelova, Valentina B., Agavni A. Ayrapetyan, Ismail T. Bataev, and Valentina V. Akasheva. "THE ESSENCE, CLASSIFICATION AND SIGNS OF CORPORATE FRAUD." EKONOMIKA I UPRAVLENIE: PROBLEMY, RESHENIYA 5/1, no. 125 (2022): 27–32. http://dx.doi.org/10.36871/ek.up.p.r.2022.05.01.004.
Full textAbstract:
The article examines the essence of corporate fraud with the identification of its inherent features; the classification of the subject of the study is given. Strengthening the financial position of an organization is often hindered by corporate fraud. The well-being of any organization primarily depends on the elimination of all threats that interfere with its normal functioning, including corporate fraud. Since many organizations meet with them, the topic of the study is relevant.
19
Shamila, Bashir Sumira Jabin Saima Jabin. "Detecting Mobile Money Laundering Using KPCA as Feature Selection Method." LC International Journal of STEM (ISSN: 2708-7123) 2, no. 3 (2021): 1–8. https://doi.org/10.5281/zenodo.5751721.
Full textAbstract:
In recent years, mobile phone payment systems have been extensively used in developed countries. Frauds are affecting the economy of the whole world. Different kinds of mobile money frauds are credit card, bank fraud, insurance fraud and financial fraud. In this paper, we discussed financial fraud and proposed an effectiveness method for money laundering. Payment system in fraud divided into four parts, point of sale, mobile payment platform, mobile payment independent and bill payment through mobile. Mobile phones are great source of service for financial transactions. Our objective is to identify the misuse of mobile money transaction and to prevent fraud from financial transaction to save the money. Financial Action Task Force (FATF) is an organization that views internationally money laundering. Financial Action Task Force continuously strengthens its standards for dealing with new risks. The Financial Action Task Force monitors countries to ensure the implementation the Financial Action Task Force Standards and holds countries to account that do not comply. This paper proposes hybrid Kernel Principal Component Analysis method used on as feature selection method and investigates the performance of Decision Tree and Boost classification Machine learning method. We applied Area under the ROC curve (AUC) and confusion matrix after using the feature selection method. We found the results of Decision Tree Training, testing and Boost with different Sampling of both datasets and Boost has better performance than Decision Tree.
20
I. VasanthaKumari, Kandoori Jaya Prasad, and Amujala Poorna Abishek. "INTELLIGENT CLASSIFICATION OF FINANCIAL TRANSACTIONS USING REAL-TIME MACHINE LEARNING TECHNIQUES." International Journal of Engineering Research and Science & Technology 21, no. 3 (1) (2025): 56–61. https://doi.org/10.62643/ijerst.2025.v21.n3(1).pp56-61.
Full textAbstract:
Real-time financial fraud detection has become increasingly vital for financial institutions due to the surge in digital transactions and the growing complexity of fraudulent activities. Traditional fraud detection methods, which relied heavily on rule-based systems and manual oversight, often failed to adapt to emerging fraud tactics, leading to high false positive rates and delayed responses. Earlier approaches using statistical models and threshold-based techniques proved insufficient in identifying sophisticated, evolving fraud patterns. The integration of machine learning has transformed this landscape, enabling systems to learn from historical transaction data and accurately detect subtle signs of fraud. The push toward AI-driven solutions is driven by the demand for rapid, automated fraud detection that minimizes human error and financial losses. Traditional systems struggle with adaptability, precision, and scalability, which limits their effectiveness. In contrast, the proposed AIbased approach utilizes machine learning algorithms such as support vector machines and decision trees to analyze transaction data in real time. This enhances detection speed, improves accuracy, and delivers a scalable, robust solution to combat fraud in today’s dynamic digital ecosystem.
21
Onwubiko, Cyril. "Fraud matrix: A morphological and analysis-based classification and taxonomy of fraud." Computers & Security 96 (September 2020): 101900. http://dx.doi.org/10.1016/j.cose.2020.101900.
Full text
22
Deepika, K., M. Pavan Sai Nagenddra, M. Vamshi Ganesh, and N. Naresh. "Implementation of Credit Card Fraud Detection Using Random Forest Algorithm." International Journal for Research in Applied Science and Engineering Technology 10, no. 3 (2022): 797–804. http://dx.doi.org/10.22214/ijraset.2022.40702.
Full textAbstract:
Abstract: Credit card fraud processing is presently the most frequently arising problem in the present world. This is due to the rise in both online transaction and ecommerce platforms. To detect these fraudulent activities the credit card fraud detection system was introduced, this project main aim is to focus on the machine learning algorithms. The voting based classification algorithm approach is applied for credit card fraud detection. We use different types of classification algorithms such as SVM, Naïve bayes and Random forest. We consider their results based on confusion matrix for the above classification algorithms. We analyze their performance based on accuracy, precision, recall and f1-score. We compare random forest algorithm with other algorithm. We considered random forest algorithm has greatest accuracy, precision, recall and F1-score, considered as the best algorithm that is used to detect the fraud. Keywords: Fraud detection, Naive Bayes, SVM, and Random Forest.
23
Yin, Pei, Wen-long Jiang, Zi-jie Ma, and Li-ke Zhang. "Cryptocurrency Transaction Fraud Detection Based on Imbalanced Classification With Interpretable Analysis." International Journal of Intelligent Information Technologies 20, no. 1 (2024): 1–21. http://dx.doi.org/10.4018/ijiit.357696.
Full textAbstract:
This study introduces an interpretable imbalanced data classification method for detecting cryptocurrency transaction fraud. We address data imbalance using SMOTE oversampling and data augmentation through contrastive learning. Next, we introduce a Transformer-based deep learning model that learns sample relevance. The model undergoes pre-training with a contrastive loss and fine-tuning through Bayesian optimization to effectively extract high-dimensional, higher-order, and fraud-related features. We employ a SHAP-based interpreter along with attention scores to elucidate the role of various transaction features in fraud detection. Comparative results demonstrate the model's remarkable recall performance in identifying cryptocurrency transaction fraud. Furthermore, it achieves an excellent F1 value, striking a balance between accuracy and recall. This research not only enriches financial fraud detection but also enhances cryptocurrency transaction security, promotes market development, and contributes to economic stability and social security.
24
Kumar Yaragani, Vinay. "An Overview of Classification Techniques and Methodologies for Fraud Detection." International Journal of Science and Research (IJSR) 13, no. 10 (2024): 927–33. http://dx.doi.org/10.21275/sr241009095246.
Full text
25
Capraş, Isabella Lucuţ, and Monica Violeta Achim. "Analysis and Classification of Corporate Fraud Based on the Literature and Investigated Cases in Romania." Studies in Business and Economics 19, no. 2 (2024): 155–75. http://dx.doi.org/10.2478/sbe-2024-0031.
Full textAbstract:
Abstract Corporate fraud has become increasingly common and sophisticated in today’s complex economic world, and a variety of strategies for perpetrating fraud have arisen. Financial fraud has various negative implications in the corporate sector since it reduces efficiency and undermines confidence and loyalty among all stakeholders. In this context, the aim of this article is to identify the various types of corporate fraud by describing and categorizing them based on the motivation and purpose for which they are committed; additionally, different types of corporate financial crimes were examined in a case study for Romania. Data for this study were gathered from past research on the subject as well as other national databases on financial crime. Tax evasion, financial statement manipulation, and bankruptcy fraud to deceive financial data users are among the various types of fraud examined. Financial fraud in organizations is a continually changing topic. The findings suggest that corporate fraud must be prevented at multiple levels, including corporate governance, internal control and external regulation. This study contributes to the existing body of knowledge on corporate fraud and can be utilized as a resource by managers and regulators looking to better understand fraud and strengthen governance and internal control systems.
26
Sinha, Akshansh, and Shivam Mokha. "Classification and Fraud Detection in Finance Industry." International Journal of Computer Applications 176, no. 3 (2017): 45–52. http://dx.doi.org/10.5120/ijca2017915570.
Full text
27
Dolgieva, M. M. "Classification of Deepfake Fraud and Cyber Kidnapping." Actual Problems of Russian Law 19, no. 11 (2024): 106–13. https://doi.org/10.17803/1994-1471.2024.168.11.106-113.
Full textAbstract:
The development of artificial intelligence technologies naturally entails the transformation of digital crime and the emergence of completely new types of crimes previously unknown to domestic criminal legislation. The use of deepfake technologies in committing fraud, as well as the so-called cyber kidnapping of a person (persuading him under deception to leave his place of residence and hide from his relatives) with the purpose of extorting a ransom for his «release» is a completely new form of cybercrime, the social danger of which is recognized at the highest legislative level. The classification of the above-mentioned acts under the current criminal law is of necessity and does not fully cover the elements of the crime, primarily its objective side. In this regard, the author proposes two ways of developing criminal legislation: the introduction of criminal liability for the use of deepfake technologies when committing encroachments on property relations in a separate provision of the law or as classifying features of existing bodies of crimes. The second option is an explanation by the Plenum of the Supreme Court of the Russian Federation as to specification of the methods of committing such crimes and actions as part of the objective side of illegal deprivation of liberty, which will make it possible to form a uniform judicial practice.
28
Jurgovsky, Johannes, Michael Granitzer, Konstantin Ziegler, et al. "Sequence classification for credit-card fraud detection." Expert Systems with Applications 100 (June 2018): 234–45. http://dx.doi.org/10.1016/j.eswa.2018.01.037.
Full text
29
Agustino, Rano, Nur Asniati Djaali, and Mutia Restu Ayuningtias. "Exploring the Effectiveness of Data Mining Classification Algorithms in Credit Card Fraud Detection." Siber Journal of Advanced Multidisciplinary 2, no. 2 (2024): 213–19. http://dx.doi.org/10.38035/sjam.v2i2.198.
Full textAbstract:
Credit card fraud is a widespread problem that impacts both individuals and companies. Data mining provides a powerful solution to not only detect but also prevent this type of fraud. This research explores this approach by utilizing data mining classification techniques to determine the potential for fraudulent credit card transactions. Data from various sources is collected and processed to extract relevant features. This research will compare 8 classification algorithms, namely Naive Bayes, Decision Trees, Artificial Neural Network, SVM, Linear Regression, Logistic Regression, LDA and Random Forest, in classifying transactions as legitimate or fake. These findings suggest that the combined use of these data mining classification methods offers a powerful tool in combating credit card fraud. To combat the problem of credit card fraud and maintain financial security for both individuals and institutions, this researcher explores the power of data mining. By using potential classification techniques, this research aims to predict fraudulent transactions on credit cards.
30
Sushkov, Viktor. "Classification and systematisation of fraud schemes identified in a financial statement audit." Auditor 10, no. 6 (2024): 10–20. http://dx.doi.org/10.12737/1998-0701-2024-10-6-10-20.
Full textAbstract:
The paper evaluates the scale of fraud and analyzes the role of auditing in its detection. Differences between corporate fraud and fraud in the context of auditing are identified. Fraud schemes related to illegal appropriation of assets and fraudulent financial reporting, including improper asset valuation, timing differences, overstatement or understatement of revenues and expenses, as well as inadequate disclosure of information, are systematized. Each scheme is illustrated with examples. Special attention is given to the peculiarities of applying fraudulent schemes in the Russian accounting practice. The research results are intended to simplify the process of assessing the fraud risks and developing responsive procedures during the audit of financial statements. The developed methodological approaches may be of interest to practicing auditors and other professionals in the field of financial control and analysis.
31
Liu, Jian, Xin Gu, and Chao Shang. "Quantitative Detection of Financial Fraud Based on Deep Learning with Combination of E-Commerce Big Data." Complexity 2020 (December 23, 2020): 1–11. http://dx.doi.org/10.1155/2020/6685888.
Full textAbstract:
At present, there are more and more frauds in the financial field. The detection and prevention of financial frauds are of great significance for regulating and maintaining a reasonable financial order. Deep learning algorithms are widely used because of their high recognition rate, good robustness, and strong implementation. Therefore, in the context of e-commerce big data, this paper proposes a quantitative detection algorithm for financial fraud based on deep learning. First, the encoders are used to extract the features of the behaviour. At the same time, in order to reduce the computational complexity, the feature extraction is restricted to the space-time volume of the dense trajectory. Second, the neural network model is used to transform features into behavioural visual word representations, and feature fusion is performed using weighted correlation methods to improve feature classification capabilities. Finally, sparse reconstruction errors are used to judge and detect financial fraud. This method builds a deep neural network model with multiple hidden layers, learns the characteristic expression of the data, and fully depicts the rich internal information of the data, thereby improving the accuracy of financial fraud detection. Experimental results show that this method can effectively learn the essential characteristics of the data, and significantly improve the detection rate of fraud detection algorithms.
32
Gurav, Prof R. B., Mrs Shraavani Mandar Badhe, Mrs Sakshi Nagtilak, Mr Sarthak Pandit Sonawane, and Mr Siddhant Agarwal. "Credit Card Fraud Detection." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (2022): 2009–12. http://dx.doi.org/10.22214/ijraset.2022.41594.
Full textAbstract:
Abstract: Now a day’s online transactions have become an important and necessary part of our lives. It is vital that credit card companies are able to identify fraudulent credit card transactions so that customers are not charged for items that they did not purchase. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Such problems can be tackled with Machine Learning with its algorithms. This project intends to illustrate the modelling of a data set using machine learning with Credit Card Fraud Detection. The Credit Card Fraud Detection Problem includes modelling past credit card transactions with the data of the ones that turned out to be fraud. This model is then used to recognize whether a new transaction is fraudulent or not. Our objective here is to detect 100% of the fraudulent transactions while minimizing the incorrect fraud classifications. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analyzing and preprocessing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data. Keywords: Credit Card, Python, Detection
33
Gurav, Prof R. B., Mrs Shraavani Mandar Badhe, Mrs Sakshi Nagtilak, Mr Sarthak Pandit Sonawane, and Mr Siddhant Agarwal. "Credit Card Fraud Detection." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (2022): 2009–12. http://dx.doi.org/10.22214/ijraset.2022.41594.
Full textAbstract:
Abstract: Now a day’s online transactions have become an important and necessary part of our lives. It is vital that credit card companies are able to identify fraudulent credit card transactions so that customers are not charged for items that they did not purchase. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Such problems can be tackled with Machine Learning with its algorithms. This project intends to illustrate the modelling of a data set using machine learning with Credit Card Fraud Detection. The Credit Card Fraud Detection Problem includes modelling past credit card transactions with the data of the ones that turned out to be fraud. This model is then used to recognize whether a new transaction is fraudulent or not. Our objective here is to detect 100% of the fraudulent transactions while minimizing the incorrect fraud classifications. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analyzing and preprocessing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data. Keywords: Credit Card, Python, Detection
34
Gurav, Prof R. B., Shraavani Mandar Badhe, Sarthak Pandit Sonawane, Siddhant Agarwal, and Sakshi Nagtilak. "Credit Card Fraud Detection." International Journal for Research in Applied Science and Engineering Technology 10, no. 5 (2022): 3499–509. http://dx.doi.org/10.22214/ijraset.2022.42920.
Full textAbstract:
Abstract: Now a day’s online transactions have become an important and necessary part of our lives. It is vital that credit card companies are able to identify fraudulent credit card transactions so that customers are not charged for items that they did not purchase. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Such problems can be tackled with Machine Learning with its algorithms. This project intends to illustrate the modelling of a data set using machine learning with Credit Card Fraud Detection. The Credit Card Fraud Detection Problem includes modelling past credit card transactions with the data of the ones that turned out to be fraud. This model is then used to recognize whether a new transaction is fraudulent or not. Our objective here is to detect 100% of the fraudulent transactions while minimizing the incorrect fraud classifications. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analyzing and preprocessing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data. Keywords: Credit Card, Python, Detection
35
Ademola, Sefiu A., W. Oladimeji Ismaila, I. O. Omotosho, and Folasade M. Ismaila. "Evaluation of Selected Machine Learning Techniques in Feature Extraction based Fraud Detection System in Online Transactions." International Journal of Recent Research in Mathematics Computer Science and Information Technology 11, no. 2 (2024): 1–13. https://doi.org/10.5281/zenodo.13897705.
Full textAbstract:
<strong>Abstract:</strong> The recent advances of e-commerce and e-payment systems have sparked an increment in financial fraud cases such as credit card fraud. Several classification techniques have been employed to detect credit card frauds in online transactions but their performances were affected by high cardholder’s data dimensionality. Thus, work employed Ant Colony Optimization for features extraction and evaluate its effectiveness using three selected classifiers. to detect fraud in credit cards online transactions. 3200 cardholders data (real and simulated) dataset with mix of genuine and fraudulent transactions. Ants Colony Optimization technique was used to extract features from the transactional data. Then, fraud detection system was designed with the three selected machine learning techniques (Back Propagation Neural Network, BPNN, Support Vector Machine, SVM and Naïve Bayes, NB) for classification. The results revealed that without features selection technique, NB, BPNN and SVM produced 86.4%, 88.7%, 93.6%, for accuracy respectively and while with ACO technique, the results or NB, BPNN and SVM produced 95.3%, 96.8%, and 97.6%. <strong>Keywords:</strong><em> </em>Fraud Detection System, Back Propagation Neural Network, Support Vector Machine, Naïve Bayes, Ants Colony Optimization. <strong>Title:</strong> Evaluation of Selected Machine Learning Techniques in Feature Extraction based Fraud Detection System in Online Transactions <strong>Author:</strong> Ademola Sefiu A., Ismaila W. Oladimeji, Omotosho I. O., Ismaila Folasade M. <strong>International Journal of Recent Research in Mathematics Computer Science and Information Technology</strong> <strong>ISSN 2350-1022</strong> <strong>Vol. 11, Issue 2, October 2024 - March 2025</strong> <strong>Page No: 1-13</strong> <strong>Paper Publications</strong> <strong>Website: www.paperpublications.org</strong> <strong>Published Date: 07-October-2024</strong> <strong>DOI: https://doi.org/10.5281/zenodo.13897705</strong> <strong>Paper Download Link (Source)</strong> <strong>https://www.paperpublications.org/upload/book/Evaluation%20of%20Selected%20Machine%20Learning-07102024-1.pdf</strong>
36
Alfarago, Dio, and Azas Mabrur. "Do Fraud Hexagon Components Promote Fraud in Indonesia?" ETIKONOMI 21, no. 2 (2022): 399–410. http://dx.doi.org/10.15408/etk.v21i2.24653.
Full textAbstract:
This study provides information about the likelihood of the natureof fraud companies so that investors and stakeholders can makebetter decisions. The Beneish model and the fraud theory aretwo well-developed ideas for understanding fraud motivationsand detecting earnings manipulation in a corporation. Unlikeprevious studies using the fraud triangle, this study uses the latesttheory (the fraud hexagon) perspective to detect fraud actions.Thus, this study aims to examine the applicability of the fraudhexagon components in combination with the M-score fromthe Beneish model. Seventy-six manufacturing firms listed onIndonesia Stock Exchange from 2015 to 2019 were chosen assamples. The findings confirmed that enterprises with fraud tendto: be more financially stable, be more leveraged, have higherprofitability, have cooperation projects with the government, havemore related-party transactions, have more auditor changes, beless liquid, less changing directors, be less supervised, and lessdisplay CEO.’s picture.JEL Classification: K40, K42
37
Ethan Brooks and Daniel Mercer. "Logistic regression on banking fraud." World Journal of Advanced Engineering Technology and Sciences 7, no. 2 (2022): 334–48. https://doi.org/10.30574/wjaets.2022.7.2.0132.
Full textAbstract:
Bank fraud has been an increasing concern for banks as fraudsters use more advanced methods to take advantage of weaknesses in online transactions. Banks use machine learning algorithms to detect fraud, and logistic regression has been among the most popular methods used to detect fraud. This paper examines the use of logistic regression for the detection of banking fraud and its benefits, use, and limitations. The article begins with a background of banking fraud, listing common types such as credit card fraud, identity fraud, loan fraud, and insider fraud. It then goes on to logistic regression, explaining why it is suitable for fraud detection and how it compares to other classification models. Data gathering, data preprocessing, and principal features that affect fraud classification are treated in the article. Moreover, the paper discusses logistic regression model building and assessment using performance metrics such as accuracy, precision, recall, and F1-score. Some of the issues such as imbalanced data, false positives, and privacy concerns are taken into consideration, and ethical and legal concerns informing fraud detection systems are discussed. How banks optimize fraud detection by integrating logistic regression with cutting-edge methods such as deep learning and blockchain technology is also explored in the paper. Finally, the paper discusses the future of banking fraud detection with an emphasis on AI innovation and emerging technologies that will shape the future of financial security. Through the adoption of machine learning and new fraud prevention strategies, financial institutions can mitigate fraud risks while providing a secure and seamless banking experience.
38
Korobkova, O. K., and D. M. Dyganova. "FRAUD AS A THREAT TO THE ECONOMIC SECURITY OF ECONOMIC ENTITIES." Vestnik of Khabarovsk State University of Economics and Law, no. 2(112) (May 31, 2023): 71–75. http://dx.doi.org/10.38161/2618-9526-2023-2-070-075.
Full textAbstract:
This article examines the essence of fraud, its conceptual apparatus. Based on the analysis of the types of fraud, a generalized classification has been compiled. Organizational and general social fraud prevention measures are proposed to ensure the economic security of economic entities.
39
Malviya, Manisha. "Improved Credit Card Fraud Detection Employing Probabilistic Back Propagation in Neural Networks." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 03 (2025): 1–9. https://doi.org/10.55041/ijsrem42307.
Full textAbstract:
With increased internet usage, online transactions have been on the rise. One of the most prevalent problems faced is credit cards frauds. While web applications and mailing services are heavily spammed, the upsurge of handheld mobile devices has led to an outburst of heavy mobile credit card spamming. The matter is more severe in mobile devices due to lesser sophisticated filtering mechanisms in built in mobile operating systems. Recent advancements in electronic commerce and communication systems have significantly increased the use of credit cards for both online and regular transactions. However, there has been a steady rise in fraudulent credit card transactions, costing financial companies huge losses every year. The development of effective fraud detection algorithms is vital in minimizing these losses, but it is challenging because most credit card datasets are highly imbalanced. This work proposes a supervised machine learning algorithm to be trained to detect credit card frauds based on the Bayes Net with penalty based regularization. It is shown that the proposed approach attains higher classification accuracy compared to existing work. Keywords— Credit Card Fraud Detection, Machine Learning, Feature Selection, Imbalanced Datasets, Probabilistic Classifier, Classification Accuracy
40
Ismail, Rasha Rokan, and Farah Hatem Khorsheed. "Classification of Credit Card Frauds Detection using machine learning techniques." JEECOM Journal of Electrical Engineering and Computer 5, no. 2 (2023): 153–60. http://dx.doi.org/10.33650/jeecom.v5i2.6602.
Full textAbstract:
Credit card fraud refers to the illegal activities carried out by criminals. In this research paper, we delve into the topic by exploring four different approaches to analyze fraud, namely decision trees, logistic regression, support vector machines, and Random Forests. Our proposed technique encompasses four stages: inputting the dataset, balancing the data through sampling, training classifier models, and detecting fraud. To analyze the data, we utilized two methods: forward stepwise logistic regression analysis (LR) and decision tree analysis (DT), in addition to Random Forest and support vector machine. Based on the outcomes of our analysis, the decision tree algorithm produced the highest AUC and accuracy value, achieving a perfect score of 1. On the other hand, logistic regression yielded the lowest values of 0.33 and 0.2933 for AUC and accuracy, respectively. Moreover, the implementation of forest algorithms resulted in an impressive accuracy rate of 99.5%, which signifies a significant advancement in automating the detection of credit card fraud.
41
SHPAK, Valentyn, Roman OVCHARYK, and Inna RAYKOVSKA. "Fraud and errors resulting from the outcome of audit checks: causes of their occurrence and possible consequences." Fìnansi Ukraïni 2022, no. 9 (2022): 115–28. http://dx.doi.org/10.33763/finukr2022.09.115.
Full textAbstract:
Introduction. Detection of errors, assumption of fraud facts, proof of distorted information and hidden true facts are among the objects of the auditor's research in the process of audit activity. Problem Statement. To date, the structure of fraud, classification, types of errors, and their dynamics have not been fully investigated; there is no clear structuring of the causes of fraud and errors; the trend of their change has not been fully analyzed. Purpose. To improve the categorical apparatus; to investigate and analyze the causes of their occurrence, possible consequences; conduct an analysis of the general trend of changes in the number of proven fraud facts by judicial authorities. Materials and Methods. In the research process, the following were used: actual data from audits; results of the National Development and Reform Commission of the Department of Accounting and Taxation of KKIBP. Methods used: generalization, systematization, comparison, critical analysis, grouping, evaluation, trend analysis. Results. The results of research on the nature of fraud and error are highlighted. The analysis of their structure, causes and possible consequences was conducted. Improved categorical apparatus: “fraud”, “error”. Analyzed trend changes fraud. Formed groups fraud . The results of research into the nature of the occurrence of fraud and errors are highlighted. An analysis of their structure, causes and possible consequences was carried out. The categorical apparatus of the concepts "fraud", "error" has been improved. The trend of changing fraud was analyzed. His groups have been formed. Conclusion. The grouping of fraud proposed by the authors will make it possible to identify new criteria for distinguishing (detecting) and classifying fraud, thereby improving management decision-making, which will provide a greater probability of knowing the object, and the identified causes of fraud during the audit will determine the selection of criteria for its classification. Based on the actual data of the State Statistical Service of Ukraine, the trend of decreasing the number of fraud cases has been proven. The classification of fraud and errors has, first of all, scientifically based and practical significance, which allows to build a clear system of knowledge about the latter as an object of research and to form the correct system of their detection and management.
42
Abdul Rahman, Nor Hafizah, Noradiva Hamzah, Adibah Jamaluddin, and Khairul Azman Aziz. "Establishing an Effective Internal Control System for Fraud Prevention: A Structured Literature Review." Asia-Pacific Management Accounting Journal 14, no. 3 (2019): 21–47. http://dx.doi.org/10.24191/apmaj.v14i3-02.
Full textAbstract:
This study presents a structured literature review of an effective internal control system. The purpose of this study is to explore and review articles in the field of internal control effectiveness using the Guthrie, Ricceri and Dumay (2012)’s framework. The literature indicates that effective internal control can reasonably reduce business risks and prevent occurrence of fraud. This paper reports findings, based on articles on internal control effectiveness published from 2000 to 2018. The review process was conducted in five stages, (1) formulation of research objectives to determine the classifications, boundaries, and definition; (2) the selection of journals; (3) the examination of the title and abstract of selected articles; (4) pilot test and adapted classification and (5) the classification to establish a range of descriptive statistics in order to understand the patterns emerging from the reviewed articles. The finding provide a basis for several aspects of future research of internal control effectiveness in assessing business risks for prevention of fraud. Keywords: structured literature review, internal control, fraud prevention
43
Zhang, Mei. "Evaluation Of Machine Learning Tools For Distinguishing Fraud From Error." Journal of Business & Economics Research (JBER) 11, no. 9 (2013): 393. http://dx.doi.org/10.19030/jber.v11i9.8067.
Full textAbstract:
<p>Fraud and error are two underlying sources of misstated financial statements. Modern machine learning techniques provide a potential direction to distinguish the two factors in such statements. In this paper, a thorough evaluation is conducted evaluation on how the off-the-shelf machine learning tools perform for fraud/error classification. In particular, the task is treated as a standard binary classification problem; i.e., mapping from an input vector of financial indices to a class label which is either error or fraud. With a real dataset of financial restatements, this study empirically evaluates and analyzes five state-of-the-art classifiers, including logistic regression, artificial neural network, support vector machines, decision trees, and bagging. There are several important observations from the experimental results. First, it is observed that bagging performs the best among these commonly used general purpose machine learning tools. Second, the results show that the underlying relationship from the statement indices to the fraud/error decision is likely to be non-linear. Third, it is very challenging to distinguish error from fraud, and general machine learning approaches, though perform better than pure chance, leave much room for improvement. The results suggest that more advanced or task-specific solutions are needed for fraud/error classification.</p>
44
Kiran Bala, Sakshi sharma, Meenakshi Garg, and Deeksha Verma. "Credit card fraud detection and classification by deep learning and machine learning." Global Journal of Engineering and Technology Advances 13, no. 3 (2022): 022–27. http://dx.doi.org/10.30574/gjeta.2022.13.3.0202.
Full textAbstract:
One of the most important contributors to the expansion and progression of a nation's economy is its banking and financial industry. In particular, over the recent past, there has been a significant increase in the utilization of credit and debit cards, whereby all customers trade transactions either digitally over the internet or physically at the stores. Here, the customers, banking institutions, and financial organizations are all being put in a difficult position by fraudulent actors. Because more recent technology is now readily available, internet banking has become an important avenue for commercial transactions. Fake banking activities and fraudulent transactions are serious problem that affects both the users' sense of safety and their trust in the system. In addition, fraudulent activities result in enormous losses because of the proliferation of sophisticated frauds such as virus infections, scams, and fake websites. These frauds are all examples of advanced fraud. This study makes three contributions toward the prevention of fraudulent activity involving credit card transactions.
45
Kiran, Bala, sharma Sakshi, Garg Meenakshi, and Verma Deeksha. "Credit card fraud detection and classification by deep learning and machine learning." Global Journal of Engineering and Technology Advances 13, no. 3 (2022): 022–27. https://doi.org/10.5281/zenodo.7680170.
Full textAbstract:
One of the most important contributors to the expansion and progression of a nation's economy is its banking and financial industry. In particular, over the recent past, there has been a significant increase in the utilization of credit and debit cards, whereby all customers trade transactions either digitally over the internet or physically at the stores. Here, the customers, banking institutions, and financial organizations are all being put in a difficult position by fraudulent actors. Because more recent technology is now readily available, internet banking has become an important avenue for commercial transactions. Fake banking activities and fraudulent transactions are serious problem that affects both the users' sense of safety and their trust in the system. In addition, fraudulent activities result in enormous losses because of the proliferation of sophisticated frauds such as virus infections, scams, and fake websites. These frauds are all examples of advanced fraud. This study makes three contributions toward the prevention of fraudulent activity involving credit card transactions.
46
Ossama, Cherkaoui, Anoun Houda, and Maizate Abderrahim. "A benchmark of health insurance fraud detection using machine learning techniques." IAES International Journal of Artificial Intelligence (IJ-AI) 13, no. 2 (2024): 1925–34. https://doi.org/10.11591/ijai.v13.i2.pp1925-1934.
Full textAbstract:
Health insurance fraud is a complex problem that also has a significant financial impact. Recently, with the availability of large volumes of data and the evolution of computing power, machine learning techniques have become the preferred method for fraud detection. However, the main difficulty facing researchers in this field is the lack of real data sets and the absence of reliable fraud labels. Most published studies use aggregated provider-level or simulated data to test fraud detection algorithms, which may not deliver accurate results. The present study aims to provide a more accurate assessment of fraud detection methods by using real detailed health insurance claims data to compare six of the most common supervised classification algorithms including neural networks and the use of two categorical feature preparation methods. The study was conducted under the guidance of insurance experts, who provided the fraud label inference rules and reviewed the results. A comprehensive description of the benchmarking process and an interpretation of the results are provided in this paper. The results show that supervised classification can be used effectively to detect health insurance fraud, improving detection accuracy by a factor of 4.2 (84% recall for a positive rate of 20%).
47
Ilham, Mohamad, Adi Winarno, Moch Lutfi, and Artanti Indrasetianingsih. "Handling Imbalanced Fraudulent Transaction Data Using SMOTE-Tomek and Random Forest: A Classification Approach." BEST : Journal of Applied Electrical, Science, & Technology 7, no. 1 (2025): 35–38. https://doi.org/10.36456/best.vol7.no1.10335.
Full textAbstract:
This research aims to address the class imbalance problem in fraud detection using hybrid resampling techniques, specifically SMOTE-Tomek, combined with Random Forest classifiers. Imbalanced data in fraud detection tasks can severely hinder model performance, resulting in poor detection of minority (fraud) cases. By employing SMOTE to oversample minority class instances and Tomek links to clean the borderline majority class samples, this study evaluates the effectiveness of this hybrid method in improving classification metrics. Using a benchmark credit card fraud dataset, we compare the performance of Random Forest models with and without the hybrid sampling approach. The experimental results show that SMOTE-Tomek significantly enhances recall and F1-score without sacrificing accuracy. This finding underscores the importance of using appropriate resampling strategies for improving model robustness in fraud detection.
48
Bandari, Madhu, and P. Pavan Kumar. "Intelligent Fraud Detection in IoT-Driven Transactions Using Multi-Layer Neural Classification." Journal of Neonatal Surgery 14, no. 5 (2025): 210–18. https://doi.org/10.52783/jns.v14.2924.
Full textAbstract:
When individuals conduct financial fraud in an Internet of Things (IoT) environment, it is because they have stolen the identity of another person or their credit card information and then utilised it to make fraudulent mobile transactions. Within the context of the IoT, financial fraud is a problem that is rapidly developing as a result of the growth of smartphones and internet transition services. Because financial fraud leads to monetary loss, it is necessary to have a system that is accurate for identifying financial fraud in an IoT environment. This is because financial fraud occurs in the real world. In the context of the IoT, there is an urgent requirement for a trustworthy system that can identify instances of financial fraud. This is because the use of smartphones and online transactions has become increasingly widespread. Our proposed method, which makes use of deep multi-layer classification, is comprised of two essential steps: first, we need to identify the presence of an intrusion; second, we need to identify the sort of intrusion that has occurred. In order to efficiently extract features, we make use of a technique known as Synthetic Minority Oversampling Technique (SMOTE), which results in an improvement in the classification accuracy. The foundation of our research is the utilisation of a Multiple-hidden Layer Backpropagation Neural Network (BPNN) for the purpose of distinguishing between routine operations and actions that include intrusion. Considering the multi-pronged approach ensures any potential risks is achieved. By merging these approaches into a robust and accurate fraud detection system, we have made a substantial contribution to the field.
49
R., Udayakumar, Joshi A., Boomiga S.S., and Sugumar R. "Deep Fraud Net: A Deep Learning Approach for Cyber Security and Financial Fraud Detection and Classification." Journal of Internet Services and Information Security 13, no. 4 (2023): 138–57. http://dx.doi.org/10.58346/jisis.2023.i4.010.
Full textAbstract:
Given the growing dependence on digital systems and the escalation of financial fraud occurrences, it is imperative to implement efficient cyber security protocols and fraud detection methodologies. The threat's dynamic nature often challenges conventional methods, necessitating the adoption of more sophisticated strategies. Individuals depend on pre-established regulations or problem-solving processes, which possess constraints in identifying novel and intricate fraudulent trends. Conventional techniques need help handling noise data and the substantial expenses incurred by false positives and true positives. To tackle these obstacles, the present study introduces Deep Fraud Net, a framework that utilizes deep learning to detect and classify instances of financial fraud and cyber security threats. The Deep Fraud Net system model entails the utilization of a deep neural network to acquire intricate patterns and characteristics from extensive datasets through training. The framework integrates noise reduction methods to enhance the precision of fraud detection and improve the quality of input data. The Deep Fraud Net method attains a precision of 98.85%, accuracy of 93.35%, sensitivity of 99.05%, specificity of 93.16%, false positive rate of 7.34%, and true positive rate of 89.58%. The findings suggest that Deep Fraud Net can effectively detect and categorize instances of fraudulent behavior with a reduced occurrence of misclassifications. The method exhibits potential implications for diverse domains that prioritize robust security and fraud detection, including but not limited to banking, e-commerce, and online transactions.
50
C., Dr Victoria Priscill. "Analysis of Performance on Classification Algorithms for Credit Card Fraud Detection." Journal of Advanced Research in Dynamical and Control Systems 12, SP3 (2020): 1403–9. http://dx.doi.org/10.5373/jardcs/v12sp3/20201391.
Full text