Hands-On Machine Learning for Algorithmic Trading

Precision-recall curves

When predictions for one of the classes are of particular interest, precision and recall curves visualize the trade-off between these error metrics for different thresholds. Both measures evaluate the quality of predictions for a particular class. The following list shows how they are applied to the positive class:

• Recall measures the share of actual positive class members that a classifier predicts as positive for a given threshold. It originates in information retrieval and measures the share of relevant documents successfully identified by a search algorithm.
• Precision, in contrast, measures the share of positive predictions that are correct.

Recall typically increases with a lower threshold, but precision may ...