Forecasting7 min read

From Chaos to Control: Designing a Markdown Optimization Engine with States

Markdown planning explodes when weeks, events, discount levels, and phases are modeled as separate dimensions. Collapsing each week into a single state turns it into a clean optimization problem.

Cyril Noirot

Lead Data Scientist

April 18, 2026

About the author

Cyril Noirot

Lead Data Scientist

Freelance data scientist. I design and ship decision systems — forecasting, pricing, marketing measurement, optimization — for teams making high-stakes calls.

For Markdown modeling, predict sell-through rate and not sales volume

Sales volume mixes demand and inventory effects. Sell-through rate captures what actually matters: how fast inventory clears under pricing and context constraints.

Forecasting5 min

Demand Planning des nouveaux produits : le plus grand angle mort du forecasting

Pourquoi le forecast de lancement produit est souvent un exercice politique plus qu'une estimation robuste, et comment le transformer en système probabiliste et explicable.

Forecasting10 min

Probabilistic Forecasting in Travel Retail - Part 2: Gradient Boosting Quantile Regression

Deep dive into gradient boosting trees with quantile regression for robust uncertainty estimation in travel retail forecasting.

Newsletter

Technical writing on forecasting, pricing, and decision systems. No fixed schedule, no spam.

Enter your email