Most markdown models start with the wrong target. They try to predict units sold.
But markdown is not fundamentally a sales forecasting problem. It is a stock-clearing problem.
If the objective is to understand how price, markdown depth, product attributes, inventory position, and external conditions affect the pace at which an item clears, then the model should predict sell-through rate — not raw sales volume.
At first glance, this is reasonable. Markdown affects demand, so predicting units sold seems natural.
À propos de l'auteur
Cyril Noirot
Lead Data Scientist
Data scientist freelance. Je conçois et déploie des systèmes de décision — prévision, pricing, marketing measurement, optimisation.