Enhanced fraud detection in credit card transactions using a Bayesian Gaussian mixture model approach
TL;DR
A novel machine learning approach for detecting credit card fraud using Bayesian Gaussian Mixture Model (BGMM), which contributes by processing the complex, multi-featured credit card dataset using an Autoencoder model to reduce its dimensionality.
Abstract
Financial institutions are highly concerned about credit card fraud due to its significant impact on their financial losses. Detecting fraud is challenging as fraudsters are constantly adapting to new technology. To protect customers and businesses, it is crucial to have a robust fraud detection system. This study proposes a novel machine learning approach for detecting credit card fraud using Bayesian Gaussian Mixture Model (BGMM). The study contributes by processing the complex, multi-featured credit card dataset using an Autoencoder model to reduce its dimensionality. The reduced data is clustered in a low-dimensional space using the BGMM to separate fraudulent from normal transactions. The Gibbs sampler algorithm was used to estimate the parameters in the BGMM. The proposed model was evaluated and compared with baseline models, including the Gaussian Mixture Model (GMM) with EM algorithm, K-means, Autoencoder, and Isolation Forest, on two public datasets, Kaggle ULB and IEEE-CIS, using AUC-ROC scores. The results demonstrate that the proposed method achieves the best performance on the Kaggle ULB dataset and competitive, stable performance on the IEEE-CIS dataset, achieving an AUC-ROC score of 0.9672 on the Kaggle ULB dataset and 0.5422 on the IEEE-CIS dataset under a leakage-free unsupervised learning protocol. The adoption of the proposed approach will aid financial institutions and credit card companies in enhancing their fraud detection systems, resulting in greater accuracy and efficiency in detecting fraudulent transactions.