A synthesizer is able to learn information about your real dataset, and use it to create synthetic data that matches the format and mathematical properties. Each synthesizer runs through two steps:

  1. Model: In this stage, the synthesizer uses various methods (typically machine learning) to learn a model from the real data

  2. Sample: Once the model has been learned, the synthesizer can use it to create synthetic data

All synthesizers in SDGym follow these steps. The benchmarking scripts will return several, descriptive statistics about each phase.

Which synthesizers can I use?

The SDGym library includes synthesizers that are ready to use. You can also create a custom synthesizer based on your own methods.

Use a synthesizer from the open source SDV library.

Use a basic data generator as a baseline to compare other synthesizers.

Define your own, custom technique for creating synthetic data.

Last updated

© Copyright 2023, DataCebo, Inc.