Statistics
What is precision and recall at k?
Precision at k and recall at k are evaluation metrics for ranking algorithms.
Proposed by @Al_Grigor
Card 1 of 259. Answer: Precision at k and recall at k are evaluation metrics for ranking algorithms.
Precision at k and recall at k are evaluation metrics for ranking algorithms.
Proposed by @Al_Grigor
Card 1 of 259. Answer: Precision at k and recall at k are evaluation metrics for ranking algorithms.
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.
Precision at k is the fraction of the top k recommended items that are relevant. Recall at k is the fraction of all relevant items that appear in the top k. They are the standard metrics for recommenders and search ranking, where only the first few results get seen.
Example: a user has 5 relevant items and the model's top 10 contain 3 of them. Precision@10 = 3/10 = 0.3 and recall@10 = 3/5 = 0.6. Raising k usually raises recall and lowers precision, the same tradeoff as moving a classification threshold.
Both ignore the order inside the top k: a relevant item at position 1 counts the same as one at position 10. When order matters, use mean average precision (MAP), MRR or NDCG. Pick k to match what users actually see, such as 5 results on a mobile screen.