Search
Close this search box.

How fashion label SikSilk drives 25% e-commerce growth from AI-powered on-site search

Urban streetwear brand SikSilk has seen a 25% increase in ecommerce purchases from on-site search and a 36% fall in site exits from its search pages since implementing new AI-powered site search technology.

SikSilk is a British-born fashion brand with stores across the UK, US, Australia and Spain and was previously relying on the native on-site search functionality of its ecommerce platform. It turned to Nosto to bring more sophistication to the search experience and solve various pain-points.

The new solution has improved on-site search performance by enabling SikSilk 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.

SikSilk’s native search technology didn’t provide the capability to sort products listed in search results based on availability, meaning products were being pushed that might only have had one available size in stock, for example. This could leave shoppers frustrated and meant SikSilk was vulnerable to losing potential sales. 

With Nosto’s Search, however, SikSilk has been able to create a global merchandising rule to ensure that all search results boost products with greater inventory and more SKU availability across size, color and style. 

“Being able to adjust our search results in relation to these ranking rules on a global level was key for us in optimizing our search,” says Chris Longshaw, Ecommerce Manager at SikSilk.

Another issue that had been impacting SikSilk’s on-site search performance was the fact that certain search queries weren’t retrieving all relevant products, restricting the choice of items shown to shoppers and impacting possible conversions.  

“Queries containing words such as colors, for example, were particularly problematic,” adds Longshaw. 

Since Nosto’s search technology uses self-learning algorithms that learn from shopper behaviour, those queries that were returning incomplete results (such as around colour), were quickly solved without needing manual effort from SikSilk.

Some search queries had previously been leading to no results pages—either because shoppers were using a synonym for a product that the previous search technology couldn’t detect, or because SikSilk didn’t stock the exact type of product being queried, and didn’t have alternative suggestions in place to show.

SikSilk was able to use Nosto to tackle this issue by configuring appropriate synonyms for the terms shoppers enter in search queries. For instance, it grouped ‘Jackets’ along with ‘Coats’, knowing that shoppers used these terms interchangeably. And because Nosto’s technology identified that queries for ‘boots’ were returning no results, SikSilk set up synonyms so that products from ‘footwear’, ‘trainers’ and ‘shoes’ categories would be listed for these searches.

In general, the predictive algorithms within Nosto’s Search can automatically identify and recommend relevant synonyms using behavioral data, eliminating guesswork and manual effort. The system also allows retailers to specify alternative or related products if a specific product is not available to encourage shoppers to continue browsing rather than exit the site.

SikSilk has noticed improvements around zero results pages since implementing Nosto, as Chris Longshaw explains: “With Nosto, everything we expect to appear for given queries, appears. There are definitely positives there. Additionally, the analytics give some good insights around no results queries that we didn’t have access to before. It’s helpful to see what queries are being regularly made that retrieve no results—not just for us to consider how synonyms can mitigate these, but also to highlight opportunities for the likes of our buying teams.”

Nosto’s Head of Search, Antanas Bakšys, suggests that SikSilk is far from alone in failing to use merchandising to optimize search results: 

“Our research suggests that around 65% of ecommerce 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.”

Since Nosto launched its new search solution to market in February this year, it’s picked up recognition from leading software user-reviews site, G2, earning ‘Trust badges’ for ‘High Performer’, ‘Highest User Adoption’, and ‘Fastest Implementation’ in the Ecommerce Search category. These awards reflect the high level of satisfaction from Nosto customers, as well as the wide-spanning market presence of the product.

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 IR.net