Understanding relevance and ranking

Search score

When performing a search, Search.io assigns a search 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 three score components: the keyword score, the neural score, and the boost score.

The components of the search score.

Relevance

The keyword score represents the Textual relevance of the result. In other words, how well does the search text match the content. This considers spelling, synonyms, stemming, and other language specific features.

The neural score represents the neural hash similarity of the result and the search text.

The larger of these two scores is used when calculating the overall search score, and their contribution generally comprises the majority of the total score, since most users are looking for results which match their query.

Ranking

The boost score represents the business-specific ranking of the search score. Generally comprising a smaller portion of the total score, it can be used to make Ranking adjustments to better tailor results to business requirements or to personalize search results.