Paper ID: 2410.20808

zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation

Azizjon Azimi, Bonu Boboeva, Ilyas Varshavskiy, Shuhrat Khalilbekov, Akhlitdin Nizamitdinov, Najima Noyoftova, Sergey Shulgin

The phenomenon of "black swans" has posed a fundamental challenge to performance of classical machine learning models. Perceived rise in frequency of outlier conditions, especially in post-pandemic environment, has necessitated exploration of synthetic data as a complement real data in model training. This article provides a general overview and experimental investigation of the zGAN model architecture developed for the purpose of generating synthetic tabular data with outlier characteristics. The model is put to test in binary classification environments and shows promising results on not only synthetic data generation, but also on uplift capabilities vis-\`a-vis model performance. A distinctive feature of zGAN is its enhanced correlation capability between features in the generated data, replicating correlations of features in real training data. Furthermore, crucial is the ability of zGAN to generate outliers based on covariance of real data or synthetically generated covariances. This approach to outlier generation enables modeling of complex economic events and augmentation of outliers for tasks such as training predictive models and detecting, processing or removing outliers. Experiments and comparative analyses as part of this study were conducted on both private (credit risk in financial services) and public datasets.

Submitted: Oct 28, 2024