Precision-Recall-Gain Curves: PR Analysis Done Right

By Peter A. Flach, Meelis Kull. Neural Information Processing Systems, 2015

403 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “The metrics used to evaluate the performance of the models are classification accuracy , F1 score , and area under the curve (AUC) of the receiver operating characteristic (ROC) curve [300, 301, 302].”
MISIM: An End-to-End Neural Code Similarity System (2020, methodology): “We use AP and AUPRG to measure the performance in a binary classiﬁcation setting, in which the models are viewed as binary classiﬁers that determine whether a pair of programs are similar by comparing their similarity score with a threshold.”
The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation (2020, background): “Similar to what Flach and colleagues did for their iso-metrics strategy [66], we depict a scatterplot of the MCCs and F 1 scores for all the 21 084 251 possible confusion matrices for a toy dataset with 500 samples (Fig.”
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models (2021, methodology): “Our proposed metric can be succinctly described as follows: The α -Precision and β -Recall metrics are generalizations of the conventional notions of precision and recall used in binary classiﬁcation analysis (Flach & Kull, 2015).”