article · IEEE Access
Rapid growth in credit card transactions has led to substantial global financial losses, while the resulting datasets present challenges due to high dimensionality and severe class imbalance. Existing machine learning models, including logistic regression, support vector machines, decision trees, random forests, and k-nearest neighbours, often struggle to deliver the performance required to identify unusual fraudulent patterns. To address these problems, a new fraud detection framework combines an undersampling technique to manage unbalanced transaction data with a feature selection mechanism that removes irrelevant and correlated variables. The core model employs support vector data description to establish a boundary around legitimate transactions, distinguishing them from anomalies. In addition, a modified particle swarm optimisation algorithm, termed polynomial self-learning particle swarm optimisation, improves the tuning of model hyperparameters. The effectiveness of this multi-stage approach has been demonstrated through experiments on a real credit card transaction dataset.
Financial fraud causes massive global losses, but stopping it requires systems that can process massive amounts of transaction data where fraudulent events are extremely rare. By refining how data is filtered and using anomaly-detection boundaries, this approach helps machine learning models pinpoint suspicious activities more reliably, even when faced with heavily skewed and noisy real-world records.
The framework could be applied within payment processing networks, banks, and financial technology companies seeking to improve automated fraud detection. Because the technique has been developed and evaluated on a real credit card dataset, it represents applied and tested research, though integration into operational banking infrastructure or commercial fraud monitoring software would require further implementation and testing.
AI-generated from the published abstract. Always read the original work before citing.
Credit card transactions have grown considerably in the last few years. However, this increase has led to significant financial losses around the world. More than that, processing the enormous amount of generated data becomes very challenging, making the datasets highly dimensional and unbalanced. This means the collected data is suffering from two major problems. It is characterized by a severe difference in observation frequency between fraud and non-fraud transactions, and it contains irrelevant, inappropriate, and correlated data that negatively affects their prediction performance. Consequently, it has attracted the interest of machine learning (ML), which has become a significant actor in fraud detection. ML has provided methods such as Logistic Regression (LR), Support vector machines (SVM), Decision Trees (DT), Random Forest (RF), and K-Nearest Neighbors (KNN). However, these methods cannot meet the outstanding performance required to detect and predict unusual fraud patterns. In this regard, the contribution of this paper is to propose a framework for fraud detection (FFD). At first, to overcome the unbalanced data problem, the framework uses an undersampling technique. Next, a feature selection (FS) mechanism is applied to select only relevant features. Then, a Support Vector Data Description (SVDD) is used to build the ML model. SVDD aims to create a tight boundary around regular data points to distinguish them from potential outliers or anomalies. In order to enhance optimization capability for its hyperparameters C and σ, a modified version of the Particle Swarm Optimization (PSO) algorithm, Polynomial Self Learning PSO (PSLPSO), is proposed. As a result, the framework’s effectiveness is shown in the experimental results on a real credit card transaction dataset.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2023.3323842
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.
