Relevance is a measurement of how well a document matches a query. To determine which documents are most relevant for a given query, Sajari leverages advanced search algorithms and machine learning capabilities. That way, Sajari not only takes into account the frequency with which the search terms appear in documents, but also user behavior and business data to achieve the most relevant results.
When performing a search, Sajari assigns a relevance score to each document in the index. The score ranges from 0 (no match) to 1 (perfect match) and search results are ordered starting with the highest score. The relevance score consists of two score components, the index score and the feature score.
The index score represents the textual relevance of the total score. In other words, how well does the search text match the content of the documents. This takes into account spelling, synonyms, stemming and other language specific features. The index score generally makes up the vast majority of the relevance score since matching content is what most users are looking for.
The feature score represents the business specific relevance of the total score. Generally making up a smaller portion of the total score, it can be used to make ranking adjustments to better tailor results to business requirements, implement promotions and merchandising strategies, or add personalization to search results.