article · Applied Computational Intelligence and Soft Computing
Rising credit card usage for online transactions has led to an increase in fraudulent activities, presenting a major challenge for financial institutions. Machine learning systems designed to identify fraud often struggle with high-dimensional feature vectors and imbalanced datasets. To address this, a two-stage hybrid methodology combines the bio-inspired firefly optimisation algorithm with a support vector machine. In the first phase, the firefly algorithm operates alongside the CfsSubsetEval feature selection technique to identify an optimal feature subset. In the second phase, a support vector machine classifier uses these optimised features to detect fraudulent transactions. When evaluated in a comparative analysis, this hybrid method reached an accuracy of 85.65% across 591 successfully classified transactions, outperforming existing non-optimisation machine learning models while reducing incorrect classifications and associated misclassification costs.
Credit card fraud causes substantial financial losses for institutions and consumers globally. By tackling common machine learning hurdles such as high data dimensionality and imbalanced transaction records, enhanced detection models can more reliably spot suspicious activity. This helps financial organisations cut the operational and economic costs tied to misclassifying legitimate purchases or missing actual fraud.
This method is targeted at financial institutions and payment processors seeking more accurate transaction monitoring systems. By improving feature selection prior to classification, the approach reduces the operational costs of misclassification. Given that evaluation was carried out comparatively on transaction data, the technology represents applied and tested research that requires further pipeline integration before being suitable for real-time commercial banking environments.
AI-generated from the published abstract. Always read the original work before citing.
The usage of credit cards is increasing daily for online transactions to buy and sell goods, and this has also increased the frequency of online credit card fraud. Credit card fraud has become a serious issue for financial institutions over the last decades. Recent research has developed a machine learning (ML)-based credit card fraud transaction system, but due to the high dimensionality of the feature vector and the issue of class imbalance in any credit card dataset, there is a need to adopt optimization techniques. In this paper, a new methodology has been proposed for detecting credit card fraud (financial fraud) that is a hybridization of the firefly bio-inspired optimization algorithm and a support vector machine (called FFSVM), which comprises two sequential levels. In the first level, the firefly algorithm (FFA) and the CfsSubsetEval feature section method have been applied to optimize the subset of features, while in the second level, the support vector machine classifier has been used to build the training model for the detection of credit card fraud cases. Furthermore, a comparative study has been performed between the proposed approach and the existing techniques. The proposed approach has achieved an accuracy of 85.65% and successfully classified 591 transactions, which is far better than the existing techniques. The proposed approach has enhanced classification accuracy, reduced incorrect classification of credit card transactions, and reduced misclassification costs. The evaluation results show that the proposed FFSVM method outperforms other nonoptimization machine learning techniques.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1155/2022/1468015
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
