Ads
Published
Apr 14, 2023
Reading time
2 minutes
Download
Download the article
Print
Text size

SilkSilk e-tail rises as it uses AI-powered search

Published
Apr 14, 2023

We’ve been hearing a lot recently about how artificial intelligence (AI) is going to revolutionise search. But while some of the most advanced AI hasn’t yet seen widespread adoption and is still fairly experimental, AI is already having an impact on fashion e-tail.


SilkSilk



Sports-meets-streetwear brand SilkSilk has been able to generate a big increase in e-commerce purchases from on-site search after revamping its search technology using an AI-powered search solution, we’re told.

And while releases about such things can sometimes read as simply an exercise in praising the tech provider, a claimed e-commerce boost of 25% can’t be easily dismissed.

SilkSilk worked with AI-Powered Commerce Experience Platform (CXP) Nosto and also said it has seen a 36% fall in site exits from its search pages since implementing new AI-powered site search technology. 

The new tech has enabled it to “merchandise the products that appear in search results in line with inventory levels, while also increasing relevancy and preventing ‘dead-end’ searches in which no products or an incomplete list of products are shown”.

SilkSilk, which also has stores across the UK, US, Australia and Spain, was previously relying on the native on-site search functionality of its e-commerce platform. That tech didn’t provide the capability to sort products listed in search results based on availability, so products were being surfaced that might only have had one available size in stock.

Additionally, certain search queries weren’t retrieving all relevant products with queries containing words such as colours, for example, being “particularly problematic”.

Its new solution ensures all search results boost products with greater inventory and more SKU availability across size, colour and style.

It uses self-learning algorithms that learn from shopper behaviour and don’t need manual effort from SikSilk. In general, the predictive algorithms automatically identify and recommend relevant synonyms using behavioural data, eliminating guesswork and manual effort. The system also allows retailers to specify alternative or related products if a specific product is unavailable to encourage shoppers to continue browsing rather than exit the site.
 
As well as the 25% increase in e-commerce purchases mentioned, Nosto’s Head of Search, Antanas Bakšys, said its research suggests around 65% of e-commerce brands don’t currently use merchandising to improve search performance.

"Merchandising can help you ensure search results are relevant while also highlighting the products you want shoppers to see and act on, such as products with high inventory, trending and seasonal items or related products with higher profit margins”.
 
The SilkSilk experience comes as research Nosto conducted earlier this year showed US and UK retailers across fashion, beauty and home & garden attribute around 39% of all traffic bouncing to poorly performing search, or because shoppers can’t find relevant products. 
 

Copyright © 2024 FashionNetwork.com All rights reserved.