Recall@k

Recall@k is a standard information retrieval metric. For example, suppose that we computed recall@10 equal to 40% in our top-10 recommendation system. This means that 40% of the total number of the relevant items appear in the top-k results.

More formally we have:

$$Recall@k = \frac{\text{number of recommended items @k that are relevant}}{\text{total number of relevant items}}$$

recall_at_k[source]

recall_at_k(predictions:List[int], targets:List[int], k:int=10)

Computes Recall@k from the given predictions and targets sets.

Arguments:

• predictions (list[int]): The list of recommended items
• targets (list[int]): The list of relevant items
• k (int): The number up to where the recall is computed - default: 10

predictions = (5, 6, 32, 67, 1, 15, 7, 89, 10, 43)
targets = (15, 5, 44, 35, 67, 101, 7, 80, 43, 12)

assert recall_at_k(predictions, targets, 5) == .2, 'Recall@k should be equal to 2/10 = 0.2'

Precision@k

Precision@k is a standard information retrieval metric. For example, an interpretation of precision@k computed at 80% could be that that 80% of the total number of the recommendations made are relevant to the user.

More formally we have:

$$Precision@k = \frac{\text{number of recommended items @k that are relevant}}{\text{number of recommended items @k}}$$

precision_at_k[source]

precision_at_k(predictions:List[int], targets:List[int], k:int=10)

Computes Precision@k from the given predictions and targets sets.

Arguments:

• predictions (list[int]): The list of recommended items
• targets (list[int]): The list of relevant items
• k (int): The number up to where the recall is computed - default: 10

predictions = (5, 6, 32, 67, 1, 15, 7, 89, 10, 43)
targets = (15, 5, 44, 35, 67, 101, 7, 80, 43, 12)

assert precision_at_k(predictions, targets, 5) == .4, 'Recall@k should be equal to 2/5 = 0.4'