Which packs should sit at which price points?
Compare demand response and economics across pack sizes, SKUs and channels rather than applying one portfolio-wide rule.
Price Pack Architecture · CPG & Beverages
Choose the right price and pack move, not one average elasticity.
Compare how price, pack size, SKU and channel changes affect demand, margin and portfolio mix before changing the commercial architecture.
Questions this decision model answers
Start with the commercial or operational choice.
What happens to units, revenue and margin?
Translate candidate moves into commercial scenarios so teams can see the expected economic consequence.
Will demand move to another pack?
Model substitution and cross-price effects where the data supports a credible estimate.
Should the same move apply everywhere?
Allow price and pack response to differ by retailer, channel, customer group or geography.
From data to decision
Build the decision around portfolio response.
The model combines granular demand response with product economics and practical commercial constraints.
Sales, price, pack and context
Use units or volume, net price, pack size, promotions, distribution, channel, customer and relevant demand drivers.
Estimate demand response
Model own-price and cross-price behaviour at the most useful level supported by the data.
Compare candidate architectures
Test feasible combinations of price, pack and channel moves against revenue, margin and volume outcomes.
Recommend the commercial move
Return the candidate architecture, expected impact, assumptions and constraints for commercial review.
Decision boundary
Elasticity is an input. Portfolio architecture is the decision.
A price-elasticity coefficient can tell you how demand responds to price. Price Pack Architecture adds the portfolio question: which pack should play which role, at which price, in which channel? See price elasticity modelling for the response layer.
Estimate demand response
Quantify how candidate moves are expected to change demand.
Control for confounding
Separate price and pack response from promotions, distribution, seasonality and other drivers where needed.
Choose the portfolio move
Compare feasible combinations against margin, revenue, volume and portfolio constraints.
Related decision problems
Follow the decision chain.
Related guide
Price elasticity modelling
Estimate price response before building the broader portfolio decision.
Related guideAssortment optimisation
Decide which products and packs should remain in the range.
Related guidePromotion incrementality
Separate causal promotion effect from base price and demand.
Direct answers
Questions buyers ask about this decision.
Is Price Pack Architecture the same as price elasticity?
No. Elasticity estimates demand response to price. Price Pack Architecture uses that response together with pack size, product roles, channel differences, margin and portfolio effects to choose a commercial architecture.
Can you model substitution between packs?
Yes, where the data contains enough variation to support it. Cross-price and substitution effects are especially important when one pack can steal demand from another.
Can the model work by retailer or channel?
Yes. The decision can be estimated at the level where there is enough reliable data, including retailer, channel, market, SKU or pack.
What comes out?
Typical outputs include candidate price and pack moves, expected unit, revenue and margin effects, substitution estimates and the constraints or assumptions behind the recommendation.
Decision IntelligenceFrom signal and prediction to a governed business action.AutoMLAutomate repetitive model-building work without losing business context.Causal Machine LearningSeparate drivers from correlations and estimate intervention effects.Predictive AnalyticsForecast demand, score customers and anticipate business outcomes.Decision OptimisationCompare feasible actions and rank them by expected business impact.Forecasting vs OptimisationSee where prediction ends and the business decision begins.Decision APIDeliver recommendations, expected impact and evidence into workflows.Embedded Decision IntelligenceAdd a decision layer to ERP, CRM, BI, workflow and vertical software.Build vs BuyA practical framework for deciding whether to build, buy or embed.
Bring the decision, constraints and data you already have.
We will structure the model around the action your team needs to take and the evidence required to support it.