Generative AI-Driven Synthetic Data Augmentation for Addressing Class Imbalance in Machine Learning Models

DOI

10.2991/978-94-6239-789-7_13How to use a DOI?

Keywords

Generative Artificial Intelligence; Synthetic Data Augmentation; Class Imbalance; Generative Adversarial Networks (GANs); Variational Autoencoders (VAEs); Minority Class Enhancement; Machine Learning; Bias Reduction; Deep Learning; Model Generalization

Abstract

Class imbalance has been a challenging phenomenon for supervised learning, resulting in biased classifiers that are biased towards the majority classes and show poor performance for minority classes. This paper presents a Generative AI-based synthetic data augmentation framework that attempts to alleviate the effects of imbalanced data. This approach exploits the capabilities of deep generative learning techniques, such as GANs and VAEs, for the generation of synthetic data for minority classes. This framework combines data preprocessing, generative model training, synthetic data validation, and model retraining into a single Python-based framework. Experiments conducted with the proposed approach show significant improvements in metrics such as precision, recall, F1-score, and balanced accuracy, along with a reduction in the overall bias towards majority classes. When compared with traditional resampling methods, the generative model-based synthetic data augmentation shows better generalization and robustness. This demonstrates the potential for the development of synthetic data generation techniques for improving the overall performance and fairness of imbalanced machine learning classifiers.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Errolla Pragnya
AU  - Kuppam Akash
AU  - Reema Lalit
PY  - 2026
DA  - 2026/10/08
TI  - Generative AI-Driven Synthetic Data Augmentation for Addressing Class Imbalance in Machine Learning Models
BT  - Proceedings of theInternational Conference on Innovation and Practices in Artificial Intelligence (ICIPAI 2026)
PB  - Atlantis Press
SP  - 172
EP  - 183
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-789-7_13
DO  - 10.2991/978-94-6239-789-7_13
ID  - Pragnya2026
ER  -