Close this search box.

How Otto has used machine learning to automate replenishment

This is an archived article - we have removed images and other assets but have left the text unchanged for your reference

European retailer Otto is using machine learning to ensure it and its partner retailers hold the level of stock that it predicts its customers will want to buy.

Otto , a Leading retailer in IREU Top500 research, sells more than 2.2m items from 6,000 brands via These include products from third-party retailers. Before it introduced the new technology, items bought through its partner retailers took between five and seven days to reach the customer. Since the process was automated, using technology from retail machine learning specialists Blue Yonder, Otto can deliver items that are stocked by these third-party retailers in between one and two days.

The technology uses machine learning and artificial intelligence to analyse the past sales, prices and stock levels from some 3bn transactions. As a result Otto says it is providing a better customer experience while generating increased demand for products. Otto has used Blue Yonder technology for several years – and has now expanded its use of the supplier’s machine learning solution to include goods from partner retailers, which are sent directly from the retailer to the customer. The solution enables it to predict which items will be sold in coming days, and how often, in what size, colour and quantity. The technology analyses about 200 factors to create accurate demand forecasts. Blue Yonder Replenishment Optimisation then uses those forecasts to deliver automated decisions.

Michael Sinn, director of category support at Otto, said: “The benefits of automated decisions becomes evident when you put it into practice,” said Mr Sinn. “We consider it accurate when we sell out of items ordered from our retail partners within 30 days. With automated replenishment decisions from Blue Yonder, we achieve this 90% of the time. This is extremely valuable for us.”

The approach has also reduced the number of returns, as customers receive the item that is the right size and the right colour.

“Otto’s strategy shows how imperative machine learning is to improving customer satisfaction,” said Professor Dr Michael Feindt, chief scientist and founder of Blue Yonder. “Everyone profits from automated replenishment processes: The customers through shorter delivery times, the suppliers through improved planning oversight, as well as higher demand. Otto gains through lower warehouse and shipping costs.”

So far, Otto has used the solution for ordering fashion and multimedia items from third-party sellers. It is looking to expand its application to its own offerings. Otto has also been able to continuously increase the number of suppliers using the reliable system.

Read More

Register for Newsletter

Group 4 Copy 3Created with Sketch.

Receive 3 newsletters per week

Group 3Created with Sketch.

Gain access to all Top500 research

Group 4Created with Sketch.

Personalise your experience on