Abstract
Objectives: Credit fraud is a global threat to financial institutions due to specific challenges like imbalanced datasets and hidden patterns in real-life scenarios. The objective of this study is to propose a model that effectively identifies fraudulent transactions. Methods: Methods such as Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN) that artificially generate synthetic data are used in this paper to approximate the distribution of data among the two classes in the original dataset. After balancing the dataset, the individual models Multi-Layer Perceptron (MLP), k- Nearest Neighbors algorithm (kNN) and Support Vector Machine (SVM) are trained on the augmented dataset to establish an initial improvement at the data level. These base-classifiers are further incorporated into the Optimized Stacked Ensemble (OSE) learning process to fit the meta-classifier which creates an effective predictive model for fraud detection. All base-classifiers and the final Optimized Stacked Ensemble (OSE) have been implemented to critically assess and evaluate their performances. Findings: Empirical results obtained in this paper show that the quality of the final dataset is considerably improved when Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN) are used as oversampling algorithms. The Multi-Layer Perceptron model showed an increase of 10% in the F1 Score while kNN and SVM showed an increase of 3% each. The optimized model is built using a Stacking Classifier that combines the GAN-improved Multi-Perceptron Model with the other standard classification models such as KNN and SVM. This ensemble outperforms the existing enhanced Multi-Layer Perceptron with near-perfect accuracy (99.86%) and an increase of 16% in F1 Score, resulting in an effective fraud detection mechanism. Novelty: For the current dataset, the Optimized Stacked Ensemble model shows an increase of 16% in F1 Score as compared to the existing Multi-Perceptron model. Keywords: Ensemble; Credit Card; Fraud Detection; GAN; SMOTE; MLP
Highlights
The usage of counterfeit or stolen credit cards is referred to as Credit card fraud and is closely related to the crime of identity theft
Implemented a model based on Multi-Layer Perceptron (MLP) and Generative Adversarial Networks (GAN) to distinguish fraudulent transactions from normal transactions and observed a 10% increase in F1 score when the augmented dataset is tested during experimental study
The study of imbalanced datasets and ensemble learning paradigms is crucial in the field of fraudulent deductions and other similar studies
Summary
The usage of counterfeit or stolen credit cards is referred to as Credit card fraud and is closely related to the crime of identity theft Institutions such as banks are responsible for detecting and blocking such kinds of transactions. There are a few stand-alone methods and algorithms, such as anomaly detectors, which show decent accuracy in classifying the non-fraudulent transactions but tend to fail with classifying the fraudulent ones due to the lack of insufficient data [1]. This is tested further in the paper. Since the F1 score takes into account both the recall and precision, it provides the trade-off that is being looked for in this study, and is considered best suited for real-life transactional scenarios
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
