Using generative adversarial networks for improving classification effectiveness in credit card fraud detection
By Ugo Fiore, Alfredo De Santis, F. Perla, P. Zanetti, Francesco Palmieri. Information Sciences, 2017
532 citations recorded by the source corpus.
Abstract In the last years, the number of frauds in credit card-based online payments has grown dramatically, pushing banks and e-commerce organizations to implement automatic fraud detection systems, performing data mining on huge transaction logs. Machine learning seems to be one of the most promising solutions for spotting illicit transactions, by distinguishing fraudulent and non-fraudulent instances through the use of supervised binary classification systems properly trained from pre-screened sample datasets. However, in such a specific application domain, datasets available for training are strongly imbalanced, with the class of interest considerably less represented than the other. This significantly reduces the effectiveness of binary classifiers, undesirably biasing the results toward the prevailing class, while we are interested in the minority class. Oversampling the minority class has been adopted to alleviate this problem, but this method still has some drawbacks. Generative Adversarial Networks are general, flexible, and powerful generative deep learning models that have achieved success in producing convincingly real-looking images. We trained a GAN to output mimicked minority class examples, which were then merged with training data into an augmented training set so that the effectiveness of a classifier can be improved. Experiments show that a classifier trained on the augmented set outperforms the same classifier trained on the original data, especially as far the sensitivity is concerned, resulting in an effective fraud detection mechanism.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/3bf418882a9de772eed10b3177f92f541d1735a6
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sanjay Chawla
- Raghavendra Chalapathy
- A. Taha
- Chong Zhou
- Yezheng Liu
- Zhe Li
- Jianshan Sun
- Yuanchun Jiang
In Computer Vision and Pattern Recognition
- A. Taha
- Chong Zhou
- Raghavendra Chalapathy
- M. Wang
- Sanjay Chawla
- Xiangnan He
- Sharaf Jameel Malebary
- Tat-seng Chua
Citations in the corpus
- Deep Learning for Anomaly Detection: A Survey (2019, background): “5 Fiore et al. [2017], Choi and Jang [2018] DNN Section 11.”
- Generative Adversarial Active Learning for Unsupervised Outlier Detection (2018, background): “Such as the abnormal trajectory and moving object detection [1], [2], [3], fraud detection [4], [5], emerging topic detection [6], [7], and medical information detection [8], [9].”
- An Intelligent Approach to Credit Card Fraud Detection Using an Optimized Light Gradient Boosting Machine (2020, background): “[21] proposed a scheme to make synthetic instances based on generative adversarial networks to enhance credit card fraud detection performance by solving the issue of the imbalanced data set.”
- Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning (2020, unknown): “[16] propose to oversample by training a GAN with the Vanilla GAN loss on only the minority class observations.”