Burke Introduces a New Framework for Assessing Synthetic Data Quality

CINCINNATI, June 15, 2026 /PRNewswire/ -- Burke, Inc., a leading decision intelligence consultancy, released new research examining the reliability of synthetic data for business decision-making and introduced Burke's FAR Framework™, a new approach for evaluating synthetic data quality and decision reliability.

As synthetic data options become more widely available, the key question is whether they can inform real-world decisions with confidence. Burke's research compared multiple synthetic methodologies and tested whether LLM-based synthetic panels can replace human respondents, how generative data models perform relative to synthetic panels, and whether the quality of the underlying human data remains critical in a synthetic-data world.

The study finds that while LLM-based synthetic panels can be valuable for early exploration, they are not yet reliable for decision-grade applications that rely on quantitative insight: at the commonly cited 80% accuracy level, LLM-based synthetic data produced false conclusions in roughly 60% of tested business scenarios. By contrast, methods grounded in validated respondent-level human data, known as generative data models, performed substantially better, suggesting greater potential for decision-support applications.

At the center of the study is Burke's FAR Framework, which evaluates synthetic data quality across three dimensions:

• Fidelity - Whether synthetic data aligns with the underlying source of truth.
• Authenticity - Whether synthetic responses reflect realistic variation rather than simply reproducing existing data.
• Resolution - Whether relationships between variables, segments, and business conclusions are preserved.

The study also identified a clear threshold for decision reliability at which synthetic approaches were far more likely to preserve research conclusions, offering an important signal for organizations trying to separate promising applications from the less reliable.

"Organizations are hearing increasingly strong claims about synthetic data," said Eli Moore, Vice President, Data Strategy at Burke. "The important question isn't whether synthetic data sounds like your customer. It's whether it leads to the same conclusions you would reach by talking to your customer. That is the standard that we believe matters most."

"AI is impacting how organizations generate insight and make decisions," said Thania Farrar, Senior Vice President, Corporate Innovation at Burke. "There's an opportunity to combine high-quality human data, advanced modeling, and expert judgment to create faster, smarter, more confident outcomes, while keeping real human voices at the heart of research."

"Our goal is always to help our clients make the best decisions for their business," said Tara Marotti, President & CEO of Burke. "This research allows us to help our clients feel confident about each method's strengths, limitations, and best-fit uses."

The findings are a result of the work of Burke Labs™, the organization's area dedicated to testing and accelerating new AI and technology solutions that transform respondent experiences, analytics, and reporting.

Burke, Inc. is a leading decision intelligence consultancy helping organizations accelerate growth through insights, strategy, innovation, and training powered by high-quality research, advanced analytics, and expert guidance. Founded in 1931, Burke combines rigorous measurement with human-centered consulting to help clients better understand people, markets, and opportunities.

For more information, please contact: info@burke.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/burke-introduces-a-new-framework-for-assessing-synthetic-data-quality-302800428.html

SOURCE Burke, Inc.