Variable Margins on Variable Revenues

Measure	Unit	Value
Mean profit	US$k	3,562
Chance of a profit below US$2 million	probability	21.7%

Measure	Unit	10th pct	Median	90th pct	Mean
Profit	US$k	1,429	3,269	6,051	3,562

The business question

A TV studio makes between 28 and 39 pilots a year. Each pilot earns its own revenue at a thin margin. A pilot has a 35% chance of becoming a local series, which then runs for one to five seasons: one season is the most likely, five the least.

A local series has a 20% chance of being sold to a US network as well, which pays much more per season at a much higher margin. Every pilot and every season has its own revenue and margin. The question is the profit from this year's slate, and how much of it rests on the handful of series that sell to the US.

Who it is for: Analysts of portfolios in which a few successes pay for many small bets: media, drug development, venture capital, exploration.
Main outputs: The slate's profit at P10 / P50 / P90 · the profit from pilots, local broadcasts and US sales · the chance of a year without a US sale and the profit in such a year.

How the model works

Three sheets after this one, read from left to right. Each one feeds the next.

Inputs sheet
The number of pilots (a PERT rounded to whole pilots), the chances that a pilot becomes a series and that a series sells to the US, and PERT ranges for each revenue and margin.
Slate sheet
VoseBinomial turns pilots into series and series into US sales. VoseAggregateMC adds up the seasons of a random number of series, each drawn from the seasons distribution. VoseSumProduct adds up revenue × margin over a random number of pilots or seasons, each with its own revenue and margin.
Results sheet
The profit's range, the mean profit from pilots, local broadcasts and US sales, and the profit in a year in which no series sells to the US.

ModelRisk techniques

Random sums VoseAggregateMC, VoseSumProduct
Distribution objects VosePERTObject
PERT rounded to whole pilots

Find similar models

The results in detail

Where the profit comes from

Mean profit from each source, and its share of the mean total.

Source	Unit	Mean	Share
Pilots	US$k	289	8%
Local broadcasts	US$k	1,052	30%
US sales	US$k	2,221	62%

A year without a US sale

What the slate makes when none of its series sells to the US.

Measure	Unit	Value
Chance that no series sells to the US	probability	9.4%
Mean profit over all years	US$k	3,562
Mean of profit × (no US sale)	US$k	111
Mean profit in a year without a US sale	US$k	1,184

What moves the profit

Lowest and highest mean profit over ten equal groups of each input (VoseSimSensitivityMean).

What moves the profit (US$k)

Tornado chart: the inputs ranked by how far the mean output moves across each input’s range.

The ranking as a table 4 inputs

Input (ranked by influence)	Lowest mean	Highest mean	Rank
Profit from US sales	1,199	7,305	1
Profit from local broadcasts	1,969	5,358	2
Number of new pilots	3,214	3,965	3
Profit from pilots	3,304	3,901	4

How to read these results

Pilots barely pay for themselves; the profit comes from the few that become series, and above all from the few series that sell to the US: about two series in ten, but about 60% of the mean profit.
So the profit is wide and skewed: the 90th percentile is roughly four times the 10th. A year in which no series sells to the US, about one in ten, makes about a third of an average year.
The counts are random at every step: how many pilots become series, how many of those sell, how many seasons each runs. VoseAggregateMC and VoseSumProduct add up a random number of draws, which is why there is no table of series here.
To judge a slate, look at the whole distribution, not at one most likely series: the business is a portfolio of long shots.

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.

Download the Excel model Get the free ModelRisk trial

Inputs and assumptions

Every assumption in the model, with its uncertainty and where it comes from. The figures are illustrative.

Pilots 3 inputs

How many pilots the studio makes this year, and what each earns.

Assumption	Unit	Uncertainty	Low	Most likely	High
Number of new pilotsEach whole number from 28 to 39 can happen; 32 is the most likely.	pilots	PERT, rounded	28	32	39
Revenue per pilotEach pilot draws its own.	US$k	PERT · drawn elsewhere	120	150	250
Profit margin on a pilotPilots barely pay for themselves.	of revenue	PERT · drawn elsewhere	1%	5%	12%

Series 3 inputs

What happens to a pilot that becomes a series.

Assumption	Unit	Uncertainty	Low	Most likely	High
Chance that a pilot becomes a local series	probability	Fixed	35%
Revenue per season, local broadcastEach season draws its own.	US$k	PERT · drawn elsewhere	120	150	250
Profit margin on a local season	of revenue	PERT · drawn elsewhere	15%	25%	45%

US sales 3 inputs

A local series that is also sold to a US network.

Assumption	Unit	Uncertainty	Low	Most likely	High
Chance that a local series is sold to the US	probability	Fixed	20%
Revenue per season from the USEach season draws its own.	US$k	PERT · drawn elsewhere	240	550	1,350
Profit margin on US revenue	of revenue	PERT · drawn elsewhere	65%	70%	85%

Units and conventions

Money: US$ thousand (US$k).
Revenue and margin: Per pilot and per season; profit = revenue × margin.
Local broadcasts: Every series is broadcast locally, including those also sold to the US.

Key assumptions and limitations

Independence: Every pilot and every season has its own revenue and margin; a series' seasons are independent of whether it sells to the US.
One year's slate: The profit of this year's pilots and all the seasons of the series they lead to, not discounted.
Data: The studio is invented for this example; the figures are those of ModelRisk's earlier TV Series Profits example.

How to use it

Change the numbers of pilots, the conversion chances, revenues and margins on the Inputs sheet.
Change the seasons distribution on the Slate sheet.
Run a simulation from the ModelRisk ribbon (10,000 samples with a fixed seed are set).
Look at how the profit depends on the US sales before deciding how many pilots to make.

The tornado chart fills in after a simulation with ModelRisk’s classic engine.

ModelRisk functions used

VoseBinomial: How many pilots become series, and how many series sell to the US.
VoseDiscreteObject, VoseAggregateMC: The seasons of a random number of series: the sum of that many draws from the seasons distribution.
VosePERTObject, VoseSumProduct: Revenue × margin added up over a random number of pilots or seasons, each with its own draws.
VosePERT: The number of pilots: a PERT from 27.5 to 39.5, rounded, so each whole number from 28 to 39 can happen.
VoseInput, VoseOutput: Name the number of pilots, the profit by source and the total.
VoseSimMean, VoseSimPercentile: Statistics of the simulation.
VoseSimSensitivityMean: The tornado chart: what moves the mean profit.

Related example models

All example models

An illustrative example: the figures are invented for teaching and do not describe a real company, project or asset. Last updated 9 October 2026.

Profits from Expanding Investments (TV Series)

Profit from this year's slate