Case study
Mintel
Synthetic respondents reproduced Mintel's own moisturizer conjoint from demographics alone, with no choice data as input.
Stated
Mintel, a global market research firm, had already run a choice-based conjoint on a 50ml facial moisturizer the traditional way: field a survey to 1,000 human respondents, then field it again to a second 1,000 as a blind validation cohort. The question was whether synthetic respondents could reproduce that result closely enough to trust, and Mintel set the bar in the open beforehand: 80 to 85% would be compelling enough to carry internally.
Revealed
The model was given demographics only, no preference data and no choices from the real survey, and still tracked the human distributions at 0.79 to 0.88 Jensen-Shannon similarity across attributes. It also disagreed in a specific, legible way. Human demand fell off sharply between $34 and $48, where the model assumed a smoother decline, so the two diverged at the top of the price range. On attribute importance the model put proof and actives on similar footing, which Mintel judged more intuitive than its own data.
Numbers
Figures with provenance.
0.79–0.88
Jensen-Shannon similarity between synthetic and human choice distributions
2 × 1,000
human respondents: one wave to calibrate against, a second as blind validation
Zero
preference or choice data given to the model — demographics only
Model-predicted
Stated before the answer was known.
Predicted
Choice distributions and attribute-level preferences for a 50ml facial moisturizer, generated from demographics alone with no preference data and no choices from the real survey.
Observed
Mintel's own conjoint, fielded to 1,000 human respondents and repeated on a second 1,000 as blind validation.
Agreement
0.79 to 0.88 Jensen-Shannon similarity across attribute distributions, above the 80% bar Mintel set in advance. The two diverged at the top of the price range, where human demand drops sharply above $34 and the model assumed a smoother decline.
Mintel POC review, 2026-04-09 (Circleback meeting ps6_KyX1Vp-cqSLq6Vkgz)
Causality
Attribute-level utilities are identified, not associated. The same design that identifies them in the human data identifies them in the synthetic data, which is what makes the two comparable at all.
- Intervention
- Product attributes varied across choice tasks: format, actives, proof claim, and price, in 10 tasks across 2 blocks plus 2 shared holdout tasks.
- Outcome
- Choice share across the moisturizer set.
- Design
- Choice-based conjoint replicated on synthetic respondents, with hierarchical Bayes fit to both the synthetic and human datasets and full distributions compared rather than point estimates.
Before
Two waves of 1,000 human respondents, a multi-week field cycle per wave, and a descriptive report at the end of it. Accurate, expensive, and not repeatable when the question changed.
With Subconscious
The same conjoint run on synthetic respondents built from demographics alone, with hierarchical Bayes fit to both datasets and the full distributions compared rather than the point estimates.
Result
0.79 to 0.88 similarity across attributes, above the 80% bar Mintel set in advance, with the disagreement isolated to the top of the price range.
The best comparison we've done across all our work together.