Performance Estimation in Binary Classification Using Calibrated Confidence
This addresses the challenge of model monitoring in deployment where labels are unavailable, offering a solution for estimating various metrics beyond accuracy, though it is incremental as it builds on existing label-free estimation methods.
The paper tackles the problem of estimating binary classification performance metrics without ground truth labels by introducing CBPE, a method that uses calibrated confidence scores to estimate confusion matrix elements and derive full probability distributions for metrics like accuracy, precision, recall, and F1, with strong theoretical guarantees and valid confidence intervals.
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.