Vose SoftwareModelRisk example · Corporate finance
Sales Forecast for a New Product
Will the launch reach its business plan? Eight years of analyser and consumables sales, with the range around them.
From the model’s saved run
The forecast against the business plan
The plan multiplies the most likely values; the simulation does not.
| Measure | Unit | Value |
|---|---|---|
| Business plan: revenue over 8 years | US$m | 527 |
| Mean revenue over 8 years (simulated) | US$m | 508 |
| Chance of reaching the 8-year plan | probability | 41.3% |
| Revenue over 8 years reached in 80% of futures | US$m | 431 |
| Mean analysers installed after 8 years | analysers | 1,057 |
Line chart: 90th percentile, Median, Mean, 10th percentile, Business plan.
The business question
A medical-device company is launching a point-of-care analyser. About 2,400 hospitals could use it. Each buys one analyser for about US$150,000 and then buys consumables for it every year, worth about US$90,000 once the hospital uses it fully.
Marketing has estimated, for each year, the share of the hospitals still without an analyser that will buy one, and the range of consumables an analyser will use. The business plan multiplies the most likely values together.
But the whole adoption curve may run faster or slower than marketing expects, and consumable use is uncertain and persistent: a hospital that uses the analyser heavily in one year will tend to do so the next. The model simulates both, and compares the forecast with the plan.
- Who it is for
- Product, marketing and finance teams preparing a launch forecast or a budget; business-development and strategy teams.
- Main outputs
- Revenue by year with its range · revenue over eight years against the business plan · the chance of reaching the plan in total and year by year · the revenue reached at a chosen confidence · analysers installed · lifetime consumables per analyser, with and without correlation between years · drivers.
How the model works
Three sheets after this one, read from left to right. Each one feeds the next.
Inputs sheet
The number of hospitals; a market-acceptance factor (PERT) that speeds up or slows down the whole adoption curve; the analyser price (PERT); and, for each year, the share of the hospitals still without an analyser that buy one, and the minimum, most likely and maximum consumables per analyser.
Forecast sheet
VoseTimeSMESaturation draws the analysers placed each year from the hospitals still without one, at the adoption rates times the acceptance factor. VoseTimeSMEThreePoint draws consumables per analyser for every year from the experts' ranges, correlated between years. Revenue = analysers sold × price + analysers in use × consumables. The business plan repeats the same rows with the most likely values.
Results sheet
Revenue over eight years and in each year against the plan, the revenue reached at the chosen confidence, the range by year, the analysers installed, how correlation between years widens the range of consumables, and the drivers.
ModelRisk techniques
Find similar models
- Product
- Type
- Application
- Uses
The results in detail
Year by year
The plan against the simulated revenue (US$m), and the chance of reaching the plan in each year.
S-curve (cumulative probability) of Revenue over 8 years from the saved simulation.
| Year | Plan US$m | Median US$m | Chance of reaching it |
|---|---|---|---|
| 2027 | 8.6 | 8.1 | 39.4% |
| 2028 | 21.2 | 20.1 | 38.8% |
| 2029 | 42.5 | 40.5 | 40.1% |
| 2030 | 63.9 | 61.4 | 41.4% |
| 2031 | 81.3 | 78.1 | 41.0% |
| 2032 | 94.8 | 91.1 | 41.4% |
| 2033 | 103.9 | 100.0 | 42.2% |
| 2034 | 111.2 | 107.4 | 42.7% |
Revenue and analysers
10th percentile, median and 90th percentile.
| Measure | Unit | 10th pct | Median | 90th pct | Mean |
|---|---|---|---|---|---|
| Revenue over 8 years | US$m | 391 | 508 | 623 | 508 |
| Revenue in year 5 | US$m | 59.5 | 78.1 | 96.9 | 78.2 |
| Analysers installed after 8 years | analysers | 858 | 1,073 | 1,236 | 1,057 |
How to read these results
- The business plan multiplies the most likely values together. Because adoption is more likely to run slower than marketing expects than faster, the plan sits above the middle of the range: the chance of reaching it is below one half — about 40% in every year, as the year-by-year table shows.
- Market acceptance drives the forecast: it moves every year in the same direction. Consumables matter next; the price of the analyser hardly matters, because most of the revenue comes from consumables (the razor-and-blades model).
- Correlation between years changes the range, not the average. If consumable use is persistent, a slow year is followed by more slow years, and the total ranges more than twice as widely as it would with independent years. Leaving the correlation out would make the forecast look far more certain than it is.
- Revenue ranges more widely each year, as more of it depends on how many analysers have been placed. Plan capacity and budgets on that range, and set targets at the confidence on the Inputs sheet.
Why the correlation between years matters
Consumables per analyser over eight years (US$ thousand).
S-curve (cumulative probability) of Correlated years, Independent years from the saved simulation.
| Measure | Unit | 10th pct | Median | 90th pct | Mean |
|---|---|---|---|---|---|
| With the experts' correlation between years | 567 | 678 | 797 | 680 | |
| With independent years | 636 | 679 | 723 | 680 |
What drives the 8-year revenue
Lowest and highest mean 8-year revenue over ten equal groups of each driver (VoseSimSensitivityMean), drawn from the overall mean.
Tornado chart: the inputs ranked by how far the mean output moves across each input’s range.
The ranking as a table 3 inputs
| Input (ranked by influence) | Lowest mean | Highest mean | Rank |
|---|---|---|---|
| Market acceptance | 366.3 | 618.4 | 1 |
| Consumables level | 432.2 | 591.8 | 2 |
| Analyser price | 500.9 | 513.7 | 3 |
See it move. Open the workbook, change an input on the Inputs sheet and run the simulation: every table and chart on this page updates in Excel.
Inputs and assumptions
Every assumption in the model, with its uncertainty and where it comes from. The figures are illustrative.
Market 3 inputs
Who can buy the analyser, and how readily.
| Assumption | Unit | Uncertainty | Low | Most likely | High |
|---|---|---|---|---|---|
| Hospitals that could buy an analyserEach buys one; the market is finite. | hospitals | Fixed | 2,400 | ||
| Market acceptanceSpeeds up or slows down the whole adoption curve. | × the adoption rates | PERT | 0.40 | 1.00 | 1.30 |
| Launch year | year | Fixed | 2027 | ||
Price and consumables 3 inputs
The analyser's price; how much of its first year an analyser uses consumables, and how persistent their use is.
| Assumption | Unit | Uncertainty | Low | Most likely | High |
|---|---|---|---|---|---|
| Price of an analyserList price US$155,000; discounts for early adopters. | US$ thousand | PERT | 130 | 150 | 155 |
| Consumables in an analyser's first yearPlacements spread over the year: half a year of use on average. | of a full year | Fixed | 50% | ||
| Correlation of consumable use between yearsHeavy use in one year tends to continue the next. | 0 to 1 | Fixed | 0.80 | ||
Targets 1 input
How sure a sales target must be.
| Assumption | Unit | Value |
|---|---|---|
| Confidence for a sales targetThe target is the revenue the forecast reaches in this share of futures. | 80% |
Expert forecast by year 8 inputs
Marketing's adoption rates, and the consumables an analyser uses each year (US$ thousand).
| Year | Calendar year | Uncertainty | Low US$ thousand | Most likely US$ thousand | High US$ thousand |
|---|---|---|---|---|---|
| Year 1Launch year: early adopters, first protocols. | 2027 | PERT, by year | 40 | 60 | 80 |
| Year 2 | 2028 | PERT, by year | 50 | 75 | 100 |
| Year 3Usage grows as more tests move to the analyser. | 2029 | PERT, by year | 55 | 85 | 120 |
| Year 4Steady use from year 4. | 2030 | PERT, by year | 60 | 90 | 130 |
| Year 5 | 2031 | PERT, by year | 60 | 90 | 130 |
| Year 6 | 2032 | PERT, by year | 60 | 90 | 130 |
| Year 7The hospitals left are the slow adopters. | 2033 | PERT, by year | 60 | 90 | 130 |
| Year 8 | 2034 | PERT, by year | 60 | 90 | 130 |
Units and conventions
- Money
- US$ million (US$m); analyser price and consumables in US$ thousand.
- Years
- Year 1 is the launch year; eight years of sales.
- Adoption rate
- The share of the hospitals still without an analyser that buy one during the year.
- Business plan
- The same forecast with every estimate at its most likely value and the expected number of placements.
Key assumptions and limitations
- Market
- A fixed set of hospitals, each buying one analyser; no replacements or competitor products.
- Consumables
- An analyser installed during the year uses consumables for part of it: half, as shipped.
- Dependence
- Consumable use is correlated between years; adoption and consumables are independent of each other.
- Data
- The product and all figures are invented for this example.
How to use it
- Enter your market, prices and acceptance range, then the experts' adoption rates and consumables ranges by year.
- Press F9 on the Forecast sheet to see other possible launches.
- Run a simulation from the ModelRisk ribbon (10,000 samples with a fixed seed are set).
- Plan capacity and budgets on the range, not on the single-line plan. Set the confidence for a sales target on the Inputs sheet and read the target on the Results sheet.
Simulate this model with ModelRisk’s classic engine: it does not run in Turbo mode yet.
ModelRisk functions used
- VoseTimeSMESaturation
- Analysers placed each year: hospitals 'convert' once, at a conditional rate per year.
- VoseTimeSMEThreePoint
- Consumables per analyser for every year from the experts' minimum, most likely and maximum, with a correlation factor between years.
- VosePERT
- Market acceptance and the analyser price.
- VoseInput, VoseOutput
- Name the drivers and the outputs, including the revenue of every year.
- VoseSimMean, VoseSimPercentile, VoseSimProbability
- Statistics of the simulation for the tables and charts on the Results sheet: the target at the chosen confidence, the chance of reaching each year's plan.
- VoseSimSensitivityMean
- The tornado chart: every VoseInput ranked by how far the mean 8-year revenue moves across its range.
Further reading
- Sensitivity analysis in Excel: a tornado chart step by step (Vose guide)
- ModelRisk help: Subject Matter Expert (SME) time series forecasts.
- Vose, D. (2008). Risk Analysis: A Quantitative Guide, 3rd edition. Wiley — forecasting with expert estimates.
Download the workbook and run it yourself. It opens in Excel with ModelRisk. The free trial runs every example model.
Related example models
- ModelRisk★★★★★Three-Statement Forecast and Funding RiskWill the company stay within its bank covenants?Five years of linked income statement, balance sheet and cash flow, with a revolver, dividends and covenant tests in every iteration.
- ModelRisk★★★★★Company Valuation with Terminal-Value UncertaintyIs the price right?A five-year DCF with a terminal value, two ways; growth and margin correlated through a copula.
- ModelRisk★★★★★Currency and Interest-Rate ExposureHow much cash could currency and interest-rate moves cost, and how much does hedging half of it save?Three correlated market prices simulated together (VoseTimeMultiGBM) over twelve quarters; a hedging policy.
An illustrative example: the figures are invented for teaching and do not describe a real company, project or asset. Last updated 9 October 2026.