Consumer & Retail
Case StudyKiabi

Kiabi increases in-store product availability by 7% by optimising supply chain management with machine learning

Kiabi is piloting machine learning to analyse historic sales data to improve its supply chain management. Its forecasting extends to predicting demand for seasonal and permanent product stock using a supply management platform to also ensure orders from suppliers are put in on time.

Context

Intensified competition in the ready-to-wear clothing retail sector has increased the variety and seasonal style ranges that stores must stock in order to meet customer demand. Retailer Kiabi now stocks six different collections per year, which requires an increased precision in inventory planning and management, and supply chain oversight.

The Project

Kiabi has implemented Infor''s Retail Demand Management tool which optimises supply chain management, such as minimum order size and time to fulfill an order. It does so by predicting sales for each clothing SKU based on historic data and local market data, such as store openings, competition, etc. along with daily warehouse stock levels and store inventory data. It predicts sales trends on a country level by looking at localised market data to aid with financial planning. The envisioned final implementation will be able to predict inventory needs on a store-level.

Data

Historic sales data, daily stock levels and store sales

Results

Product availability has improved from 90% to 97% on permanent collection items, sales forecasts are more reliable and stock shortages less frequent.

Back to Case Studies
AI Daily Brief — leaders actually read it.

Free email — not hiring or booking. Optional BPAI updates for company news. Unsubscribe anytime.

Include

No spam. Unsubscribe anytime. Privacy policy.