Compare Features

Compare the features available across SDV Community and SDV Enterprise. SDV Enterprise users also have the option of purchasing SDV Bundles, which are optional add-on packages for targeted needs.

AI-Based Synthesizers

These synthesizers use AI to learn patterns from your data and use them to recreate synthetic data.

SDV Community
SDV Enterprise

GaussianCopula statistical AI

CTGAN, TVAE, CopulaGAN neural networks

XGC advanced Copula modeling with flexible shapes, faster runtime and more

SegmentSynthesizer for separately modeling highly segmented data

BootstrapSynthesizer for modeling data with a few rows

DPGC, and DPGCFlex Synthesizers for creating synthetic data with differential privacy guarantees

PAR for sequential data

HMA multi-table for limited tables (<5)

HSA multi-table for unlimited tables

Independent multi-table for unlimited tables

Performance estimates for multi-table synthesizers with various dataset sizes

Test Data Synthesizers

These synthesizers create random test data based on metadata alone. They do not use AI so you do not need to input any training data.

SDV Community
SDV Enterprise

DayZSynthesizer single table

DayZSynthesizer multi table

Data Integrations

These features make it easy to integrate the SDV into your application and pipeline.

SDV Community
SDV Enterprise

Auto-detect metadata using data CSVs or DataFrames

Auto-detect metadata based on your database

Directly connect to a database for importing real data and creating metadata

Connect to a database for exporting synthetic data

Pre-Process Statistical Information

Transformers are used to pre-process your data, which can improve data quality. SDV synthesizers select transformers by default, but you can always customize these to your dataset.

SDV Community
SDV Enterprise

FloatFormatter for missing value imputation, numerical columns

ClusterBasedNormalizer and GaussianNormalizer statistical transforms

XGaussianNormalizer with support for 100+ statistical distributions

ECDFNormalizer to normalize any distribution with high fidelity

Uniform, Label, and OneHot Encoding for discrete variables ( and )

Datetime Encoding including datetime format parsing, and converting timezones

Learning timezones that are attached to your datetime column

OutlierEncoder for numerical outliers

DPECDFNormalizer, DPDiscreteECDFNormalizer for normalizing a column while guaranteeing differential privacy

Understand & Anonymize Real-World Concepts

Transformers are used to pre-process your data, which can improve data quality. SDV synthesizers select transformers by default, but you can always customize these to your dataset.

These transformers are geared towards columns that correspond to industry or domain-specific concepts. Their structure may be human-created.

SDV Community
SDV Enterprise

RegexGenerator, IDGenerator for keys and IDs

AnonymizedFaker general-purpose anonymization

PsuedoAnonymizedFaker for general pseudo-anonymization with a mapping

Emails understanding domains

Addresses understanding locations

Phone Numbers understanding country and area codes

GPS Coordinates understanding geographical areas and distances

Constraint-Augmented Generation

Input business rules into your synthesizer using constraints. This ensures high-quality, valid synthetic data, 100% of the time.

SDV Community
SDV Enterprise

Predefined logic for individual tables: FixedIncrements, FixedCombinations, Inequality, OneHotEncoding, Range

Program your own constraint for single tables

Advanced, predefined logic for individual tables: ChainedInequality

Advanced predefined logic for individual tables: FixedNullCombinations, MixedScales

Advanced, predefined logic for multi-table tables: CarryOverColumns, CompositeKey, ForeignToPrimaryKeySubset, UniqueBridgeTable, and more.

Support for programming your constraint and additional predefined logic

Synthetic Data Evaluation

Evaluate your synthetic data by comparing it against the real data.

Public SDV
SDV Enterprise

Access to SDMetrics library vendor-agnostic, open source

Diagnostic Report basic data validity checks , single and multi-table

Quality Report statistical similarity, single and multi-table

Measure the privacy of your data: DisclosureProtection and DisclosureProtectionEstimate

Visualization 1D and 2D bars, scatterplots, heatmaps and more

Use case-specific metrics: OutlierCoverage, SmoothnessSimilarity

Last updated