Confidence Bands for ROC Curves

Abstract

We address the problem of comparing the performance of classifiers. In this paper we study techniques for generating and evaluating confidence bands on ROC curves. Historically this has been done using one-dimensional confidence intervals by freezing one variable-the false-positive rate, or threshold on the classification scoring function. We adapt two prior methods and introduce a new radial sweep method to generate confidence bands. We show, through empirical studies, that the bands are too tight and introduce a general optimization methodology for creating bands that better fit the data, as well as methods for evaluating confidence bands. We show empirically that the optimized confidence bands fit much better and that, using our new evaluation method, it is possible to gauge the relative fit of different confidence bands.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2003
Accession Number
ADA453849

Entities

People

  • Foster J. Provost
  • Michael L. Littman
  • Sofus A. Macskassy

Organizations

  • New York University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Binomials
  • Case Studies
  • Computer Science
  • Data Mining
  • Data Sets
  • Information Retrieval
  • Information Science
  • Machine Learning
  • New York
  • Normal Distribution
  • Probability
  • Sampling
  • Test Sets

Readers

  • Neural Network Machine Learning.
  • Regression Analysis.
  • Semiconductor Device Technology

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference