MMMM Studio

This was a quick preview. It is wrong in a known direction — every range below is narrower than the truth, so it looks more certain than it is. Run it in full before you quote anything.

You came in with six guesses. Here is what your data did to each one.

The pale shape is what you believed before the model saw anything. The solid shape is what it concluded afterwards. If the solid shape is much narrower, your data taught it something. If it sits in the same place at the same width, the number is your own assumption dressed up as a result — and you should treat it that way.

TV — BroadcastMeasured
BREAK-EVEN05.6

99%

narrower than your guess. The data narrowed the range by 99% and the model settled cleanly.

guessed $1.22 · concluded $1.23 ($0.93$1.72)

Paid SocialMeasured
BREAK-EVEN05.8

97%

narrower than your guess. The data narrowed the range by 97% and the model settled cleanly.

guessed $1.22 · concluded $0.83 ($0.46$1.61)

Video — CTVMeasured
BREAK-EVEN05.6

97%

narrower than your guess. The data narrowed the range by 97% and the model settled cleanly.

guessed $1.22 · concluded $0.87 ($0.47$1.62)

Paid SearchMeasured
BREAK-EVEN05.6

96%

narrower than your guess. This channel's spending pattern closely tracks another's, so the split of credit between them is uncertain.

guessed $1.22 · concluded $1.38 ($0.82$2.25)

Out of HomeMeasured
BREAK-EVEN05.4

95%

narrower than your guess. The data narrowed the range by 95% and the model settled cleanly.

guessed $1.22 · concluded $0.79 ($0.39$1.66)

Programmatic DisplayMeasured
BREAK-EVEN05.6

93%

narrower than your guess. The data narrowed the range by 93% and the model settled cleanly.

guessed $1.22 · concluded $0.97 ($0.46$2.18)

How do I read this?

What happened, week by week

Every period’s outcome split into the baseline the business would have earned anyway and the incremental effect of each channel. The black line is what actually happened. Each channel’s weeks add up to exactly the contribution reported on the overview — this is the same calculation, drawn out over time rather than summed. The shaded band at the right was held out of the fit entirely, so the model was never shown it.

$5.0M/WK13 WEEKS WE HID FROM THE MODEL →2022202320242025
TV — Broadcast2.7%
Paid Search1.9%
Paid Social1.3%
Video — CTV1.1%
Programmatic Display1.0%
Out of Home0.6%
Everything else91.4%
What you actually soldthe line
On the weeks it learned from
typically 5.8% outover 195 periods · 89% of the movement explained
On the weeks we hid from it
typically 13.0% outover 13 periods · tracked the movement worse than a flat line would
No better than assuming nothing and repeating the same period last year, which would have been 10.4% out.