LinkedIn / case study
← All selected workSeparating the base from the event.
A commercial forecast designed to distinguish underlying sales from the lift created by commercial events.
OutcomeMTD forecast · base vs event lift
Evidence levelUnverifiedScale or method documented; quantitative impact, adoption or net savings still need confirmation.
StackPython · machine learning · commercial analytics
01 / Context
The question behind the work.
A month-to-date number can hide two different realities: the underlying sales pattern and the temporary effect of a commercial event. The decision needed both.
02 / Built
Structure before decoration.
Structured the forecasting problem around a baseline and event effect, then created a workflow that could be reviewed by the business instead of presenting an unexplained number.
03 / Result
What changed.
The forecast gave commercial conversations a clearer starting point: what the business was already on track to sell, and what the event appeared to add.
This case study is intentionally anonymised. It describes the shape, scale and outcome of the work without exposing internal data, client systems or confidential screenshots.
Continue