Application of Artificial Intelligence for Fraudulent Banking Operations Recognition
Bohdan Mytnyk,
Oleksandr Tkachyk,
Nataliya Shakhovska
et al.
Abstract:This study considers the task of applying artificial intelligence to recognize bank fraud. In recent years, due to the COVID-19 pandemic, bank fraud has become even more common due to the massive transition of many operations to online platforms and the creation of many charitable funds that criminals can use to deceive users. The present work focuses on machine learning algorithms as a tool well suited for analyzing and recognizing online banking transactions. The study’s scientific novelty is the development… Show more
“…The findings revealed that ANN performed well, with an F1 score of 0.91. Regarding banking transaction fraud detection context, Mytnyk et al [14] have compared seven machine learning models: RF, k-nearest neighbors (KNN), LR, stochastic gradient descent (SGD), decision tree (DT), naive Bayes (NB), and SVM on a transactional dataset. According to the findings of the various methods, the LR works better, yielding a final AUC value of around 94.6%.…”
Digital trades and payments are becoming increasingly popular, as they typically entail monetary transactions. This not only makes electronic transactions more convenient for the end customer, but it also raises the likelihood of fraud. An adequate fraud detection system with a cutting-edge model is critical to minimizing fraud costs. Identifying fraud at the ideal time entails establishing and setting up ubiquitous systems to consume and analyze massive amounts of streaming data. Recent advances in data analytics methods and introducing open-source technology for big data storage and processing opened new options for detecting fraud. This study aims to tackle this critical issue by providing a newly real-time e-transaction fraud detection schema that consolidates the advantages of both unsupervised learners, including autoencoder and extended isolation forests, with cutting-edge big data gadgets such as Spark streaming and sparkling water. It addresses the shortage of non-fraudulent instances and handles the excessive dimension of the set of features. On two real-world transactional datasets, we assess our suggested technique. Compared with other current fraud identification systems, our methodology delivers an elevated accuracy yield of 99%. Furthermore, it outperforms state-of-the-art approaches in reliably identifying fraudulent samples. Doi: 10.28991/HIJ-2024-05-01-014 Full Text: PDF
“…The findings revealed that ANN performed well, with an F1 score of 0.91. Regarding banking transaction fraud detection context, Mytnyk et al [14] have compared seven machine learning models: RF, k-nearest neighbors (KNN), LR, stochastic gradient descent (SGD), decision tree (DT), naive Bayes (NB), and SVM on a transactional dataset. According to the findings of the various methods, the LR works better, yielding a final AUC value of around 94.6%.…”
Digital trades and payments are becoming increasingly popular, as they typically entail monetary transactions. This not only makes electronic transactions more convenient for the end customer, but it also raises the likelihood of fraud. An adequate fraud detection system with a cutting-edge model is critical to minimizing fraud costs. Identifying fraud at the ideal time entails establishing and setting up ubiquitous systems to consume and analyze massive amounts of streaming data. Recent advances in data analytics methods and introducing open-source technology for big data storage and processing opened new options for detecting fraud. This study aims to tackle this critical issue by providing a newly real-time e-transaction fraud detection schema that consolidates the advantages of both unsupervised learners, including autoencoder and extended isolation forests, with cutting-edge big data gadgets such as Spark streaming and sparkling water. It addresses the shortage of non-fraudulent instances and handles the excessive dimension of the set of features. On two real-world transactional datasets, we assess our suggested technique. Compared with other current fraud identification systems, our methodology delivers an elevated accuracy yield of 99%. Furthermore, it outperforms state-of-the-art approaches in reliably identifying fraudulent samples. Doi: 10.28991/HIJ-2024-05-01-014 Full Text: PDF
“…The authors in [2] underscore the significance of leveraging artificial intelligence for the detection of fraudulent banking transactions. They introduce several classification algorithms applied to discern transaction types based on specific features.…”
“…In addition to detecting fraud and fraud in organizations, fraud detection techniques and intelligence tools aim to predict future behavior and reduce the risk of fraud by understanding user and customer behavior. Banks and financial institutions are striving to speed up the process of identifying fraudsters due to the high costs of fraud (1)(2)(3). It is against the law to commit fraud in electronic banking and electronic money transfer.…”
In recent years, with the increase of access to customer data and the improvement of data analysis capabilities through intelligent methods, various activities have been carried out to analyze customer behavior; it is in the detection of bank frauds. Currently, bank frauds have a wide range of results, other than material and financial losses to the bank, customers and banks. After using smart tools to use different algorithms, the two selected algorithms XGBoost and LightGBM, according to the high ROC in the obtained models were selected step by step. At the same time, it has been used in final tests with the reduction of false samples labeled as fraud (FP). This model is developed using real development data and gives very acceptable results in card-to-card fraud detection. This model can significantly improve the security of the banking system and be used as a tool to reduce financial crimes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.