Reflect simulation model

Our simulation model works at the individual level, is calibrated against observed data, and adapts to the category's purchase behavior. The result is forecasts that hold up, not just in the presentation but in the market.

Reflect's simulation model rests on three principles. Individual level: every consumer is simulated separately based on their unique preference profile. Calibration: the model is validated and adjusted against observed market data (actual shares, sales, distribution). Category adaptation: the model configuration reflects the actual purchase process in the category.

Calibration is the most underestimated component. An uncalibrated conjoint simulation often produces market shares that do not match reality. This is because conjoint measures preference in a controlled environment — not in the real market with all its frictions (distribution, availability, shelf placement, advertising). Calibration corrects for this gap.

The result is a simulation tool that delivers calibrated market share forecasts, volume forecasts for price changes, cannibalization analysis for product launches, and scenario planning for assortment changes. All at the individual level, all calibrated, all category-adapted.

Upcoming visual

Reflect simulation architecture — individual-level modeling with calibration

Key takeaways

Individual-level simulation with Hierarchical Bayes profiles
Calibration against observed market data, not just survey data
Category-adapted model configuration
Calibrated market share and volume forecasts
Supports scenario planning for price, assortment and product launches

Example

A multinational food company tested Reflect's model against their existing supplier's forecasts across 12 product launches. Reflect's calibrated model had an average forecast deviation of 2.1 percentage points. The uncalibrated model deviated by 6.8 percentage points. Across 12 launches, the difference corresponded to approximately 180 MSEK in better allocated marketing budgets.

When conjoint works and when it does not

Conjoint works best when the consumer makes conscious trade-offs between clear attributes. It works poorly in low-involvement categories, with habitual behavior, and when price dominates the decision.

First choice vs share of preference

First choice shows what the consumer picks first. Share of preference shows how preference is distributed. Which metric is right depends on the category's purchase behavior, and they often give entirely different answers.

Individual level, not aggregate

The average consumer does not exist. Simulation models that work at the individual level capture heterogeneity in preferences and give markedly better forecasts than aggregated models.

How simulation should adapt to category

The same simulation model does not work in all categories. Purchase process, involvement, repertoire behavior and price sensitivity vary, and the simulation model must reflect that reality.

See related service →

Discuss your simulation models with us

← Back to Simulation that reflects real individuals, not averages

Reflect simulation model

Key takeaways

Example

Related articles