Multinational Apparel Retailer
In-Season Inventory Management

234K Active SKUs
670 Stores
20 DCs in 16 Countries
50+ Marketplaces
50 Countries

Goals

Elimination of human dependency in the initial allocation, replenishment, and store-to-store transfers processes, and provide integrated and autonomous planning

Usage of best picked statistical methods and machine learning / AI algorithms to address store-level differences in customer preferences

Decrease stock-out and lost-sales while increasing the availability through smarter inventory management process

Provide technology to support fast growth with a small allocation team

Challenges

Fast growth fueled by addition of new countries, new store openings, and new warehouses

Disconnected processes requiring larger teams with the growing complexity of the network

Need to accommodate geographical differences in seasonality and product preference across the network

Need to maximize sell-through for short lifecycle fashion products through smart initial allocation and demand-driven replenishment

Benefits

Rapid go-live in less than 4 months

Automation of initial allocation & replenishment processes

Scenario-based store-to-store transfer optimization to rebalance inventory across the network

Scalable platform supporting seamless growth across multiple countries

150M+ weekly recommendations

20% headcount reduction in allocation team
while expanding to 50 countries

0 %
user acceptance rate of daily recommendations
0 %
headcount reduction in allocation team

Solutions

5/5