Brad Mirtchler
Key takeaways
- 3:04Promotion planning must balance uncertain price elasticity and stockout risk against the working-capital and waste costs of post-promo overstocks.
- 7:07Accurate machine-learning forecasts depend on preserving promotion type, price, discount, sales before and after the campaign, and cannibalization data.
- 9:09Promotion performance should be judged through weighted forecast error as well as overstocks, inventory turnover, availability, and out-of-stocks.
- 13:12Promotion scenario planning lets retailers compare projected outcomes at different price levels before selecting a campaign configuration.
- The described European supermarket case achieved 98.9% promotional availability and reduced post-promo overstocks by 56% across 107 stores and 30,000 SKUs.
In Brad Mirtchler's words
“Promo becomes a bit of an addiction.”
Promo Forecasting 2.0: How AI Transforms Promo Planning in Grocery Retail | EuroShop 20263:04
“We simply cannot have a promotion that has an out-of-stock, or we lose the loyalty of our incoming customer who comes to our stores to shop for these things.”
Promo Forecasting 2.0: How AI Transforms Promo Planning in Grocery Retail | EuroShop 202610:09
“If we're not tracking this data today, we can't have accurate forecasts tomorrow.”
Promo Forecasting 2.0: How AI Transforms Promo Planning in Grocery Retail | EuroShop 202613:12
“Having the right stock at the end is just as important as having the right stock at the beginning.”
Promo Forecasting 2.0: How AI Transforms Promo Planning in Grocery Retail | EuroShop 202614:13