AI Tackles Forecasting Gaps in Beauty Retail
An unnamed beauty retailer's new-product demand forecasts ran nearly double actual sales, highlighting a challenge retailers are turning to AI to address.
Updated on Nov. 4, 2026 in Retail
Retailers risk holding excess inventory when demand forecasts miss, and one unnamed beauty retailer's forecasts for new products were almost twice actual demand, resulting in slow-selling products and obsolete stock. Retailers are now using AI to identify comparable products and model demand curves for new items.
Why it matters
Beauty retailers regularly introduce new items, which makes forecasting difficult and raises the cost of overstocking. Better demand modeling could help retailers decide purchasing, placement and order quantities more accurately.
Forecasts for one unnamed beauty retailer's new products were almost twice actual demand. A K-means store clustering project for fashion retailer Zadig & Voltaire lifted sell-through performance by 10 points using 28 numerical features.
The players
Zadig & Voltaire
A French fashion retailer whose store clustering project using K-means improved sell-through performance by 10 points.
The details
The team used AI to identify comparable products and analyse product type, market relevance, price tiers and seasonality. The model generated a demand curve for each new product to guide purchasing, placement and order quantity decisions.
Timeline
2026: Remarks on AI in retail were delivered at the Retail Asia Summit 2026 in Hong Kong.
Market Landscape
Store clustering with K-means, as used by Zadig & Voltaire, has become one of the more concrete applications of machine learning in apparel retail planning. Beauty retailers now seek similar gains by modeling demand for new products from comparable items.
Shoppers may see fewer sold-out or discontinued beauty products as retailers get better at matching stock to demand. Overstocked items that are later discounted could also become less common if forecasts improve.
The takeaway
Accurate forecasting for new products depends on finding truly comparable past items, so retailers that structure product data by type, price tier and seasonality are better positioned to avoid excess inventory.
Further reading
Explore more on Retail trends and how companies manage inventory and demand.
