Preserving correlations: A statistical method for generating synthetic data

arXiv:2403.01471v1 Announce Type: new
Abstract: We propose a method to generate statistically representative synthetic data. The main goal is to be able to maintain in the synthetic dataset the correlations of the features present in the original one, while offering a comfortable privacy level that can be eventually tailored on specific customer demands.
We describe in detail our algorithm used both for the analysis of the original dataset and for the generation of the synthetic data points. The approach is …

abstract arxiv correlations cs.lg data dataset eventually features generate math.pr physics.data-an privacy statistical statistical method synthetic synthetic data type