One of the most important features of a robust e-commerce site, whether it’s in the promotional products industry or beyond, is the quality of its search function. After all, if you can’t find what you’re looking for, how can you make a purchase? Hamish Ogilvy, CEO and co-founder of Search.io, a company that uses machine learning to improve internet search results, explains the power of high-quality on-site search engines.

Hamish Ogilvy, CEO and co-founder of Search.io 

Q: Why is an on-site search function so important for e-commerce?

A: E-commerce site search has the power to boost visitor experience, build customer loyalty and grow on-site conversion rates. It actually has an outsized influence on buyer and seller success. According to one study, visitors who use search can generate around 30% to 60% of all e-commerce site revenue, and on-site searchers convert at 1.8 times that of non-searchers.

On-site conversion rates hover at around 3% industry-wide, but Amazon.com enjoys a conversion rate that’s five times the industry average (it’s even higher for Prime members). Search is vital at the world’s largest marketplace for finding anything, so naturally Amazon invested heavily in search engineering for 20 years.

The good news for brands and retailers is that, with the availability of newer off-the-shelf search solutions, they don’t need to invest that much money or resources for building out their own capability.

Q: How does a quick and accurate search function improve customer experience online?

A: Online retailers know they have about 15 seconds on average to keep a customer engaged before they bounce off an e-commerce site. Shoppers are searching, but most site search solutions don’t work as people would want.

Amazon famously did a study in which they demonstrated that every 100-millisecond lag in website response time costs millions of dollars in lost revenue.

Speed and accuracy matter to visitors. I should note, too, that this includes mobile shoppers. More than half of e-commerce customers shop via phones where the user experience is different, but vitally important.

Q: Your site mentions that many brands are still relying on 20-year-old search technology. Why is that so limiting for them? What are the issues with older search functionality?

A: Search engines can’t look at something the same way people do. It’s hard for a search engine to understand user intent. For example, if someone is searching your site for a “shower curtain rod,” a search engine looks at each word in the query and needs to decide where to send you. Older search engine technology that only uses keywords might see “shower” and send you to the wrong place. These older technologies require site owners to write extensive rules to overcome these challenges.

For a retailer, it means investing hundreds of hours writing rules, synonyms and engineering hacks to make simple searches work. And the work is never done. When you make changes to your product catalog or add new products, you need to write more rules. Because it’s so time-intensive and complex, most e-tailers end up focusing on the top 20% of their catalog, leaving the other 80% unoptimized.

Q: Can you explain what an artificially intelligent search engine is and what it can do compared to traditional search functions?

A: There are two things that AI is bringing to bear right now that help online sellers. One is providing more relevant results, and the other is re-ranking results based on the data.

AI-powered search engines understand context and intent. They operate mostly without the need for human intervention (setting rules and exceptions). Instead, they “learn” from the search trends and user interactions on the site.

For online sellers, this translates into significantly less work on their part. You don’t need to stuff your product pages full of keywords, synonyms, tags and metadata. Search results just work.

That solves for relevance. But a lot of products could be relevant, so in what order should you rank them? This is where machine learning can also help by using signals to rank products in the order that’s most likely to convert. We can use data such as clicks, signups, add-to-cart, purchases, etc., to push the best-sellers, or most popular products, or highest-margin items, to the top. It could also differ by region.

There are a lot of factors to consider, and this is where AI can really help. Ultimately, we give retailers control to decide what’s most important for their business so they can configure results to work for them.

Q: Can you give some examples of how AI interprets the meaning of search queries to deliver accurate results?

A: Sure. A real example is a company we spoke with that sells seasonal products — in this case, it was Halloween clothing and costumes. If a customer is searching for, say, Halloween socks, they would need to type in “Halloween socks” to find them. But with AI-powered search, they can type “spooky socks” or “horror socks” or something like that and get the same great results. Try that with a normal search engine; it won’t work. The company didn’t have to do anything to enable the feature because the AI understands the concept of Halloween and automatically associates it with “horror” or “scary.”

Q: Anything else you’d like to add about the future of online searches?

A: Consumers are getting more and more sophisticated in their buying habits and demands for great shopping experiences. To us, search is really the starting point. Search can be leveraged to provide the kinds of interactions that were unthinkable just a few years ago. Things like personalization, merchandising and better recommendations can all be delivered through a better search experience. People often don’t realize that collection pages and product filter pages (where there’s actually no user query) are also powered by search technology.