# Measuring the quality of Synthetic data for use in competitions

arXiv: https://arxiv.org/abs/1806.11345 · HTML: https://mlsanity.com/paper/1806.11345/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark](https://mlsanity.com/paper/2310.16981/) (2023)
- [Utility Theory of Synthetic Data Generation](https://mlsanity.com/paper/2305.10015/) (2023)
- [Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms](https://mlsanity.com/paper/2301.08844/) (2023)
- [Enabling Synthetic Data adoption in regulated domains](https://mlsanity.com/paper/2204.06297/) (2022)
- [Towards a Taxonomy for the Use of Synthetic Data in Advanced Analytics](https://mlsanity.com/paper/2212.02622/) (2022)
- [Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data](https://mlsanity.com/paper/2104.00635/) (2021)
- [Synthetic Data Generator for Adaptive Interventions in Global Health](https://mlsanity.com/paper/2303.01954/) (2023)
- [Permissioned Blockchain-based Framework for Ranking Synthetic Data Generators](https://mlsanity.com/paper/2405.07196/) (2024)
- [Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review](https://mlsanity.com/paper/2504.18544/) (2025)
- [ADLGen: Synthesizing Symbolic, Event-Triggered Sensor Sequences for Human Activity Modeling](https://mlsanity.com/paper/2505.17987/) (2025)

## Abstract (arXiv)

Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sharing data in a way that compromises privacy. In order to overcome this hurdle, several methods have been proposed that generate synthetic data while preserving the privacy of the real data. In this paper we consider a key characteristic that synthetic data should have in order to be useful for machine learning researchers - the relative performance of two algorithms (trained and tested) on the synthetic dataset should be the same as their relative performance (when trained and tested) on the original dataset.