This research project includes an application of Conditional Tabular Generative Adversarial Network to synthesize tabular data. By harnessing advanced GAN architectures and tailored training strategies for tabular data synthesis, this project aspires to contribute to the field of machine learning.
The aim of this project is to leverage the potential of Generative Adversarial Network to generate synthetic data which inturn has a potential to overcome some of the issues faced during any Machine Learning model training, like:
- Lack of Data (especially labelled)
- Imbalanced Dataset
- Data Aquisition and Labelling Problem
Input: Any tabular data for training GAN Output: A synthetic dataset of the desired count
It has 2 main workflows:
- Synthetic Data Generation (using GAN)
- Synthetic Data Evaluation (using Ensemble Modeling)
