Search
Close this search box.

Recommendation engine increases Republic’s average order value by 22%

This is an archived article - we have removed images and other assets but have left the text unchanged for your reference



Fashion retailer Republic has experienced a 22% increase in average order value since adding Peerius‘ recommendation technology to its ecommerce site.

“We have been delighted with the results that we have experienced and we now find that 18% of all our orders contain a recommended product,” says Mark Kelly, Republic’s ecommerce manager. “With Peerius, we were confident that we had the best performing product in the marketplace. In addition, because of their sector focus on apparel, we knew that their system was well attuned to the specifics of our industry sector.”

“We’ve found that customers that view recommended products spend nearly 22% more on average than those that don’t and spend 65% longer on site,” he added. “What’s really encouraging is that the positive effects seem particularly acute on first-time visitors.”

Republic now also plans to use Peerius’ social search technology and personalised recommendations in its emails too.

“Peerius provides recommendations which are influenced not only by the way the user is currently browsing, but also take into account the past purchasing habits of that individual as well as purchasing patterns of similar consumers,” explains the company’s Roger Brown. “Peerius uses a hybrid approach which means we are not limited to one particular technical approach such as ‘collective behaviour’ (for example, customers who bought X often bought Y as well) or ‘collaborative filtering’ (similar users tend to purchase Z); rather we use a complex mixture of systems logic depending on what we assess the customer’s intention to be.”

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