Back to Search Start Over

From Uncertainty to Precision: Enhancing Binary Classifier Performance through Calibration

Authors :
Machado, Agathe Fernandes
Charpentier, Arthur
Flachaire, Emmanuel
Gallic, Ewen
Hu, François
Publication Year :
2024

Abstract

The assessment of binary classifier performance traditionally centers on discriminative ability using metrics, such as accuracy. However, these metrics often disregard the model's inherent uncertainty, especially when dealing with sensitive decision-making domains, such as finance or healthcare. Given that model-predicted scores are commonly seen as event probabilities, calibration is crucial for accurate interpretation. In our study, we analyze the sensitivity of various calibration measures to score distortions and introduce a refined metric, the Local Calibration Score. Comparing recalibration methods, we advocate for local regressions, emphasizing their dual role as effective recalibration tools and facilitators of smoother visualizations. We apply these findings in a real-world scenario using Random Forest classifier and regressor to predict credit default while simultaneously measuring calibration during performance optimization.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2402.07790
Document Type :
Working Paper