Data Augmentation Using Gaussian Mixture Model on CSV Files

One of the biggest challenges in training supervised models is the lack of amount of labeled data for training the model and facing overfitting and underfitting problems. One of the solutions for solving this problem is data augmentation. There have been many developments in data augmentation of the image files, especially in medical image type datasets, by doing some changes on the original file such as Random cropping, Filliping, Rotating, and so on, in order to make a new sample file. Or use Deep Learning models to generate similar samples like Generative Adversarial Networks, Convolutional Neural Networks and so on. However, in numerical dataset, there have not been enough advances. In this paper, we are proposing to use the Gaussian Mixture Models (GMMs) to augment more data very similar to the original Numerical dataset. The results demonstrated that the Mean Absolute Error decreases meaning that the regression model became more accurate.