We’re all familiar with semantic search bars — those that pick up exactly what you’re searching for, before you even finish typing your query. From Wikipedia to Amazon, these intuitive search tools are featured on websites of all kinds, and they’re undoubtedly a revolution in the e-commerce user experience.
But these query bars aren’t the end-all-be-all. In fact, there has been new technological advancements that takes smart-search capability to the next level, introducing visually-based smart search methods.
Predicting What Consumers Want
Through data mined from past engagement with the site — buying behaviors, clicks and viewing patterns — predictive algorithms produce visual, real-time search results as you type. That is, as you search, a hovering page just below the search bar shows relevant products (“Top Results”) that the algorithm has deemed the consumer ‘most-likely-to-buy’.
Testing the New System
The first company to implement this innovative technology was O’Neill Clothing — a world renowned surf brand and apparel company. And since implementation, the brand has seen incredible year over year increases in conversion. For example, in 2013 O’Neill’s conversion rate was 2.7%. But with the addition of this new search tool from Reflektion a couple months ago, its conversion rate shot up to 4.4%.
That’s a pretty serious bump, especially considering the fact that, “We high five each other if we can make a .25% change,” according to O’Neill’s CEO Daniel Neukomm.
Go to the site, search “boardshorts” and watch the magic happen – it’s pretty amazing.
The Future of Real-Time Visual Search
Remarking on the tool’s importance within the e-commerce landscape, Reflektion’s CEO Sean Moran says, “This is based on repeat visitors finding that search has become a highly efficient way to find the things they are most interested in, and subsequently, conversion rates and revenue increase quickly as well.”
That said, in addition to the program’s proven results, we wouldn’t be surprised to see many more e-commerce sites follow suit and begin to implement the search tool. At Trinity we are in the development stages of this constructing this type of add-on for enterprise search programs and will report on the results.