Research

Publications

Research documenting our methodology, statistical validation frameworks, and side-by-side comparisons of synthetic versus live panel data.

White Papers

Technical papers exploring synthetic survey methodology, validation approaches, and applications in agentic commerce and real-time preference intelligence.

White Paper

Evaluating Synthetic Survey Estimates

A comprehensive framework for evaluating the accuracy of AI-generated synthetic survey data against live panel benchmarks. Covers statistical methodology, divergence metrics, and validation protocols used across all Simsurveys domain models.

Healthcare / Methodology Download PDF →
White Paper

Synthetic Respondents for Agentic Commerce — CTO Brief

Technical brief for engineering and product leaders on integrating synthetic respondent infrastructure into agentic commerce systems. Covers real-time preference querying, probability-weighted distribution APIs, and sub-second response architectures for autonomous agent decision loops.

Consumer / Agentic AI Download PDF →
White Paper

Patient Digital Twins from Federal Public Health Data

Technical paper on building patient digital twins from publicly available federal health datasets (NHIS, MEPS, BRFSS, NHANES, CAHPS, PROMIS). Covers the methodology for constructing representative patient profiles from 500,000+ de-identified records and validating against real patient survey outcomes.

Patient / Healthcare Download PDF →

Related Academic Literature

Independent peer-reviewed research validating digital twin and synthetic respondent approaches in survey research.

Peer-Reviewed

Scaling Survey Respondent Pools with AI: The Twin-2K-500 Framework

Toubia et al. (2025) demonstrate that LLM-based digital twins can reproduce survey responses with high fidelity across 2,000 respondents and 500 questions. Published in Marketing Science, this independent research validates the core approach underlying Simsurveys' patient and consumer digital twin models.

Academic / Marketing Science View article →

Ready to Test Synthetic Data?

Create your free account and see how synthetic respondents perform for your research questions.