https://docs.protegrity.com/synthetic-data/1.0.1/docs/about_synthc_data/Recent content in About Protegrity Synthetic Data onHugoenhttps://docs.protegrity.com/synthetic-data/1.0.1/docs/about_synthc_data/hide_synthc_data_arch/Mon, 01 Jan 0001 00:00:00 +0000https://docs.protegrity.com/synthetic-data/1.0.1/docs/about_synthc_data/hide_synthc_data_arch/<p>An overview of the communication is shown in the following figure. <img src="https://docs.protegrity.com/synthetic-data/1.0.1/docs/images/sydata/hide_sd_arch_comm.png" alt="Protegrity Synthetic Data Components" title="Protegrity Synthetic Data Components"></p> <p>Protegrity Synthetic Data system includes the following core components:</p> <h2 id="key-pods-and-services">Key Pods and Services</h2> <ul> <li> <p>Synthetic Data App Pod</p> <ul> <li>Orchestrates Synthetic Data generation.</li> </ul> </li> <li> <p>MLFlow Pod</p> <ul> <li>Captures model training and evaluation.</li> <li>Hosted in containers for scalability.</li> </ul> </li> <li> <p>S3 bucket Pod</p> <ul> <li>Stores models, model artifacts, and generated reports.</li> <li>Used by both MLFlow and Synthetic Data App pods.</li> </ul> </li> <li> <p>SQL Database Server Pod</p>https://docs.protegrity.com/synthetic-data/1.0.1/docs/about_synthc_data/hide_supp_models/Mon, 01 Jan 0001 00:00:00 +0000https://docs.protegrity.com/synthetic-data/1.0.1/docs/about_synthc_data/hide_supp_models/<h2 id="models-supported-by-protegrity-synthetic-data-101">Models supported by Protegrity Synthetic Data 1.0.1</h2> <p>Protegrity Synthetic Data 1.0.1 supports tabular synthetic data generation using GAN‑based models, including TVAE and diffusion‑based techniques. These models are used to generate privacy-safe synthetic tabular data while preserving:</p> <ul> <li>Column types and schema compatibility</li> <li>Statistical distributions</li> <li>Relationships and correlations between variables</li> <li>Utility for analytics and ML workloads</li> </ul> <p>The following are the modeling techniques:</p> <ul> <li> <p><strong>Generative Adversarial Networks (GANs)</strong> – It is considered as a primary approach which is used to learn the structure and statistical properties of real tabular datasets and generate Synthetic Data.</p>