AI & Machine Learning
Cosine Similarity
A metric that measures the similarity between two vectors by the cosine of the angle between them.
Definition
Cosine similarity quantifies how similar two embedding vectors are by measuring the cosine of the angle between them, independent of magnitude. It is widely used for semantic search, recommendations, and clustering because it correlates well with perceived textual similarity. In internal linking systems, high cosine similarity between page embeddings can suggest relevant cross-links.