Enhancing public research on citizen data: An empirical investigation of data synthesis using Statistics New Zealand's Integrated Data Infrastructure

Alex X. Wang, Stefanka S. Chukova, Andrew Sporle, Barry J. Milne, Colin R. Simpson, Binh P. Nguyen

Abstract: Highlights•IDI integrates citizen data, but access restrictions hinder research.•We propose synthetic data as a solution.•We evaluate various data synthesis and machine learning algorithms.•We provide recommendations for use cases in IDI.•Our study offers insights for data science projects in IDI.