Our website uses cookies

Cookies enable us to provide the best experience possible and help us understand how visitors use our website. By browsing Essential Retail Magazine, you agree to our use of cookies.

Okay, I understand Learn more

Asos returns rate creates unique challenge for data scientists

Data scientists working at Oracle Retail experienced a returns rate pattern like no other when helping online fashion house Asos develop the most suitable algorithms for a new merchandising tool earlier this year.

The fluctuation in the retailer’s sales profile was a major challenge for the technology company during the process to implement a clearance optimisation engine that is expected to help boost Asos’s sell-through rate.

Chris Metcalf, merchandise planning tech programme manager at Asos, explained the story at the Oracle Retail Industry Forum in Barcelona, saying the combination of Asos’s popularity, its customer proposition and shopper habits contribute to “unusual” trading.

“As an online business, we get a much higher rate of returns than a store business,” he commented.

“Central to our proposition, we give hassle-free returns – all of this means you get an unusual sell-through profile in Asos compared to many other retailers.”

When a new product launches on the website, he said, sales might spike. Because Asos operates with a shallow stock pool, some sizes run out quickly so sales soon drop off, before a significant percentage of returns then find their way back into the supply chain.

“It comes back into our fulfilment centres, we re-process it, we put it back on the website and we put it up for sale again,” Metcalf added.

“You get an initial surge, a lull, and then a secondary bounce – you don’t get linear sales. While that has operational problems it is something Asos lives with and works with, but for a forecasting engine it was a level of fluctuation Oracle hadn’t seen before.”

Ultimately, Asos is pleased with the work Oracle has done to get the clearance optimisation engine up and running. Having started the project at the turn of the year, the tool is now fully in use for the first time, in time for the mid-season sales period.

Metcalf and the Asos team hope the tool will help improve sell-through, optimise markdowns and free-up what the company believes is one of the busiest merchandising teams in retail with 85,000 different products to sell.

Coming soon: Esential Retail's feature on how Asos developed its clearance optimisation tool and why the tech is expected to transform merchandising processes.

What’s Hot on Essential Retail?