The footwear giant is partnering with artificial intelligence (AI) platform provider Findmine to automatically generate complete recommended outfits when customers browse an individual product. Before leveraging the Findmine solution, Adidas merchandisers had to manually build outfits for its online “Complete the Look” recommendation feature. This process took 27 steps and 20 minutes, resulting in fewer than 10% of products appearing in outfits.
However, Adidas determined that customer average order value (AOV) significantly increased when they were presented with a recommended outfit instead of an individual item. This meant Adidas was limiting the revenue lift from e-commerce.
Adidas decided to deploy the Findmine solution, initially performing a six-week A/B test where half the traffic to Adidas.com saw manually programmed outfits and half saw outfits automatically generated by Findmine. Neither merchants nor customers could distinguish AI-based outfits from manually created outfits.
Since fully rolling out Findmine, Adidas has experienced a 95% decrease in the time merchandisers spend on Complete the Look and increased the number of items included in outfits by 960%.
“Findmine has helped us reduce the amount of manual work and has helped us ensure that our newest products have to cross-sell from day 1, improving conversion, average order value, and customer satisfaction better than any other solution we’ve tried,” said Brian Klavitter, senior director, Adidas consumer experience.