“We then realized we didn’t know internally what relevance was,” he says. He quickly began to fill that gap, so the staff could tune the results to improve sales.

Make the Sales Connection
In e-commerce, the underlying product data is typically well-structured and tagged, so the need for additional context may not be as apparent. (The tagging effort is also easier for e-commerce firms than for media companies, notes CMS Watch’s Byrne.)

Most companies know to account for common misspellings by creating internal term maps, so for example, a customer looking for pendant lights will still find them if he types “pendent” in a search query, YLighting’s Zwelling notes. (“Pendant” is misspelled in nearly half of his site’s searches.)

And most companies know that databases may not be consistent, due to human error or differences in suppliers’ own taxonomies, so additional effort is needed to also search for synonyms and to look across multiple fields for some terms, he says.

But as Zwelling discovered, customers don’t think in terms of just product specifications that match to product databases. And this requires more sophisticated work. For example, a query for “red table lamp” could miss lamps that come in a red finish but where the color choices are not called out in the database’s color field or description. But a search engine such as the SLI Systems hosted search tool that he uses can detect all red lamps despite taxonomic differences, then let customers quickly sort them by room or material, he says.

Sometimes there’s a hidden need to adjust context. At Broder Bros., which sells shirts and other items that can later be customized with company logos, executives assumed that basic keyword search was sufficient, since the company sells to distributors who know the product codes or have a paper catalog. But an analysis of search patterns showed that about 15 percent of all searches were free-form: These people were essentially researching what might be available, says Mike Fabrico, VP of IT. Broder Bros.’ search approach didn’t serve that need—and potentially lost sales. So the company replaced its search engine with one from Progress Software that could support contextual searches.

Another tip: Don’t overlook failed searches, says John Cortez, director of applications at Shaklee. He regularly monitors searches that result in no hits: This helps him identify new contextual mappings that would lead to appropriate results, and determine products that customers might want but aren’t offered. Then he can give sales an indication of potential opportunities.