Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Performance Estimation in Binary Classification Using Calibrated Confidence

About

Model monitoring is a critical component of the machine learning lifecycle, safeguarding against undetected drops in the model's performance after deployment. Traditionally, performance monitoring has required access to ground truth labels, which are not always readily available. This can result in unacceptable latency or render performance monitoring altogether impossible. Recently, methods designed to estimate the accuracy of classifier models without access to labels have shown promising results. However, there are various other metrics that might be more suitable for assessing model performance in many cases. Until now, none of these important metrics has received similar interest from the scientific community. In this work, we address this gap by presenting CBPE, a novel method that can estimate any binary classification metric defined using the confusion matrix. In particular, we choose four metrics from this large family: accuracy, precision, recall, and F$_1$, to demonstrate our method. CBPE treats the elements of the confusion matrix as random variables and leverages calibrated confidence scores of the model to estimate their distributions. The desired metric is then also treated as a random variable, whose full probability distribution can be derived from the estimated confusion matrix. CBPE is shown to produce estimates that come with strong theoretical guarantees and valid confidence intervals.

Juhani Kivim\"aki, Jakub Bia{\l}ek, Wojtek Kuberski, Jukka K. Nurminen• 2025

Related benchmarks

TaskDatasetResultRank
Performance EstimationASSISTments ID
Bias (Acc)69.5
1
Performance EstimationASSISTments OoD
Bias (Acc)43.7
1
Performance EstimationCollege Scorecard ID
Bias (Accuracy)12.7
1
Performance EstimationCollege Scorecard OoD
Bias (Accuracy)31.1
1
Performance EstimationDiabetes ID
Bias (Accuracy)12.7
1
Performance EstimationDiabetes OoD
Bias Accuracy17.4
1
Performance EstimationFood Stamps ID
Bias Accuracy0.191
1
Performance EstimationFood Stamps OoD
Bias (Acc)22
1
Performance EstimationHospital Readmission ID
Bias (Acc)41.6
1
Performance EstimationHospital Readmission OoD
Bias (Accuracy)49.4
1
Showing 10 of 16 rows

Other info

Follow for update