MAP (mean average precision) measures: area under the precision-recall curve averaged across queries

Ever wondered how search engines rank your queries?

Imagine you're searching for a recipe online and you're presented with a list of results. You want the best one to appear at the top.

The mean reciprocal rank (MRR) concept helps search engines figure out how well they're ranking the top result for your query. It's like a score that tells you how likely you are to find the best answer at the top of the list.

Example

If you asked for a chocolate cake recipe and the first result was the best one, you'd get a score of 1. If the first result was good but not the best, you'd get a score of 1/2, and so on.

Remember this

MRR gives search engines a way to measure and improve the quality of their search results.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

BLEU vs ROUGE: BLEU measures precision of n-grams, ROUGE measures recall

BLEU measures precision of n-grams, ROUGE measures recall

NDCG measures: ranking quality with graded relevance scores

Ever wonder why some search results feel more helpful than others?

to normalize features: when features have different scales and you use distance-based methods

Why do some things need to be adjusted to compare fairly?

Hierarchical navigable small world

HNSW is an efficient ANN search algorithm

score matching does: learns the gradient of the log-density without normalizing

Ever wonder how we can compare apples and oranges fairly in studies?

Euclidean geometry

Euclidean distance measures absolute position in space

Swipe through 100 ML concepts daily

Open Pocket Polymath