Google ranking systems
Google's documented list of the systems that generate rankings, distinguished from one-off 'updates' to those systems, and…
GoogleSystemConfirmed
Neural matching
AI system that connects words in a query to concepts in documents, revealed as affecting about 30% of queries.
What changed
Google disclosed neural matching at its twentieth-anniversary event, describing it as a way to relate words to concepts so that pages using different vocabulary from the query can still be matched. It said the system was already affecting roughly 30% of queries. Google has repeatedly distinguished neural matching, which is about concept matching, from RankBrain and BERT, and has said there is nothing to optimise for it directly. It remains listed among Google's ranking systems.
Timing
Rollout began 24 September 2018. No completion date was announced. Rankings typically remain unstable for the whole rollout window, so measurements taken inside it are not a reliable read on the outcome.
What it affected
Related terminology
Neural matching
A Google system that uses neural networks to understand how queries relate to page concepts, bridging vocabulary gaps between…
RankBrain
Google's first machine-learning ranking system, introduced in 2015, which helps interpret how queries relate to concepts…
Semantic search
Retrieval based on the meaning of a query and documents rather than literal keyword matching, using entities, context and…