Coveo Launches Facet Generator

Coveo Solutions, a provider of artificial intelligence-powered relevance platforms for search, recommendations, personalization, and merchandising within digital experiences, today introduced Facet Generator as part of the Dynamic Navigation Experience models, creating a navigation experience for large enterprises with complex needs.

Coveo AI delivers a dynamic, personalized site search across digital experiences without traffic or behavioral data required. By automatically adjusting the facet or filter options available for search or listing pages, Coveo has improved discoverability in commerce, service and workplace environments.

"Coveo is simplifying the implementation and configuration of site navigation for large enterprises," said Laurent Simoneau, president, chief technology officer, and founder of Coveo, in a statement. "Coveo is one of the only search platforms that can automatically leverage hundreds of filtering options and select the best ones to use to help improve the customer or employee experience without any traffic or behavioral data. Combined with the intelligence of our machine learning Dynamic Navigation Experience model, Coveo has the ability to go even deeper when data is available. As a result, our platform can help to drive unmatched relevance and personalization in website navigation."

The new Facet Generator works to automatically return all relevant search facets for a given search or listing page. This feature works with zero traffic, leveraging the intelligence within Coveo's unified index to return the most relevant results. For each query, users will automatically get precise filters to ensure they can see the most relevant options to help maximize click-through rate, conversions, and ultimately revenue.

Once behavioral data is collected based on facet interactions, Dynamic Navigation Experience can effectively reorder facets and facet values. The model learns from usage analytics events, such as search and click events, in which end users interacted with search facets and obtained the desired result items. Therefore, the more the model learns from facet-related actions performed by online shoppers, the more effectively it can re-order search facets and provide relevant search results.

Componenbts include the following:

• Facet Reordering: This feature can reorder facets based on their relevance in a given setting by leveraging both query data and contextual data.
• Facet Value Reordering: This feature can reorder values within a given facet to make the most popular values appear at the top. To do so, the models use the search events performed by previous users who selected certain facet values for specific queries.
• Facet Value Autoselection: This autoselection feature automatically selects facet values according to searches.
• Ranking Boost: This feature uses the most popular facet values to boost the search results whose field values match the popular ones.