German online retailer Zalando is using machine learning to offer a virtual fashion assistant to customers.
Called the Algorithmic Fashion Companion, the online solution is able to generate outfit recommendations in real time.
The algorithm identifies an “anchor” product based on the customer’s personal preferences, such as their wish list or previous purchases. It then builds a new outfit around this product.
The recommendations are built from machine learning based on analysing 200,000 existing outfits from Zalon, the retailer’s curated shopping service.
However, indicating that Zalando is not willing to trust a machine entirely with style matters, its stylists regularly tweak the algorithm to keep it up to date with current trends.
It will be available in all 17 Zalando markets this week. Early feedback shows that 50% of the outfits generated were considered “good”.
AFC Product Manager Marta Skassa said: “Customers often tell us that they find it difficult to combine items and that they appreciate getting inspiration and fashion advice.”
Skassa said that customers who interact with such personalisation services have a higher conversion rate and larger basket sizes.
“We can now offer this with unlimited, free outfit suggestions based on an item that they either already own, or have already expressed interest in.”
On the human element, Skassa added: “I think this proves that algorithms are really good at replicating things they have learned. Out of all the training data, the algorithm is able to create something that people generally like. Human stylists can set trends by exploring new ideas; algorithms can only follow trends.”
Other retailers exploring the potential of AI assistants include Japanese chain Uniqlo and styling service Stitch Fix.
This week also saw Zalando, along with other European ecommerce giants, co-sign a letter to European finance ministers opposing a recently mooted tax on digital services.