Comparing marketing scenarios: making assumptions and results comparable.
Evidence status
What was reproduced, and what it does not prove.
The public CSV and the Python run verify the probabilities, expectations and floors of the three allocations compared. They verify neither the scenarios, nor market probabilities, nor which risk criterion to adopt.
- Technical specification of the scenario comparison, specification in French (opens in a new tab)
v1, 31 August 2026 · CC BY 4.0 · specification in French · Method document written by marketing-mix.net. The figures are illustrative: they are not market measurements.
Key distinctions
Three conditions before calculating.
Coherent states
A market scenario combines demand, costs, media return and competitive reaction in a coherent way. Mixing every extreme independently creates an impossible stress test or double-counts the same risk.
A common base
Objective, horizon, budget, costs included, constraints and reference scenario stay identical. An option cannot look better because it ignores a cost or uses a more favourable window.
Reversibility
A monthly allocation can favour expected value and learn quickly. An annual commitment, a contract or a channel closure requires more protection against the worst case.
Method
Building a reproducible comparison before choosing the risk criterion
- 01Define the allocations
Create scenarios that are genuinely executable and sufficiently different — prudent, central and aggressive, for example — and document their common constraints.
- 02Define the states
Build three to five states from the material uncertainties, their dependencies and the available evidence, and assign probabilities only where they are defensible.
- 03Calculate a common sheet
For each cell, calculate the contribution with the same conventions, then derive expected value, minimum, dispersion, implementation cost and time to review.
- 04Connect to control
Choose the criterion according to exposure and reversibility, then define the signals that will allow a switch to another scenario.
The comparable matrix of the three allocations
Each allocation is computed with the same probabilities, cost conventions and market states, then compared by expected value, floor and reversibility.
| Allocation | Weak market Contribution €k | Central market Contribution €k | Strong market Contribution €k | Expected value | Minimum | Review | Decision |
|---|---|---|---|---|---|---|---|
| A · balanced | €180k | €270k | €330k | €255k | €180k | Monthly | Retained |
| B · aggressive | €110k | €300k | €400k | €263k | €110k | Weekly | Pilot |
| C · prudent | €210k | €240k | €280k | €239k | €210k | Quarterly | If floor ≥ 200 |
Eight thousand euros of expected value do not by themselves offset a floor lower by €70,000
Three allocations A, B and C produce respectively €180k, €270k and €330k; €110k, €300k and €400k; and €210k, €240k and €280k in the weak, central and strong states. The probabilities are 30%, 50% and 20%.
Expected values: A = €255k, B = €263k, C = €239k. Minimums: A = €180k, B = €110k, C = €210k. B gains €8k of expected value over A but lowers the floor by €70k; C raises the floor by €30k but gives up €16k of expected value.
A is kept as the compromise if the approved minimum floor is €175k. B remains a reversible learning option; C becomes preferable if the required floor rises to €200k. Minimax regret is calculated, where necessary, on the robust optimisation page.
Acceptance conditions
What must be true to act.
- 01
The allocation scenarios and the market states are coherent and executable.
- 02
Expected value, minimum, dispersion and reversibility are presented together.
- 03
The choice criterion depends explicitly on reversibility.
- 04
Signals allow a change of scenario after observation.
Limits
What this analysis does not prove.
- The matrix depends on the quality of the states retained.
- No single criterion replaces prior agreement on the floor and on reversibility.
- Subjective probabilities do not become objective through calculation.
References
Works cited.
- Schoemaker, P. J. H. (1995), “Scenario Planning: A Tool for Strategic Thinking”, Sloan Management Review, 36(2), 25–40.
- Goodwin, P. & Wright, G. (2001), “Enhancing Strategy Evaluation in Scenario Planning”, Journal of Management Studies, 38(1), 1–16.
- Keeney, R. L. & Raiffa, H. (1976), Decisions with Multiple Objectives.