Promo & Markdown Lift
Measures true incremental lift from promotions versus baseline so finance and marketing stop talking past each other.
Currently in development
Real data. Real charts. Coming Q3 2026.
Promotions feel successful in revenue but often fail on margin. This study uses pre/post comparison and a treatment-vs-control approach to isolate true incremental lift — separating real demand from purchases that would have happened anyway.
Methodology drafted · pairs naturally with the Funnel Leak Finder dataset
What this case study will show
- Define baseline using a comparable pre-promo window with seasonality controls
- Treatment vs. control segmentation — promoted SKUs/customers vs. matched non-promoted
- Decompose impact: incremental units · cannibalization · margin erosion
- Visualize lift curves by promo depth (5%, 10%, 20%, 30%) to find the efficient frontier
- Recommendation framework for go/no-go on future promos
Tools
Build timeline
1
Methodology drafted
Done
2
Build foundational case studies first
In progress · Funnel → Lifecycle → Churn
3
Treatment/control sample design
After foundation ships
4
Lift analysis + margin decomposition
Q3 2026
5
Screenshots, narrative, publish
Q3 2026
Why share this in-progress?
Because portfolios should be honest. The three live case studies — Funnel Leak Finder, Lifecycle Segmentation,
and Churn Early Warning — show the foundation of my analytics craft. This project builds on that foundation,
and I'm publishing the plan now so the work is transparent.