Concepts

These explanations dive into the what, why and theory behind each of DataEval’s features.

• Balance Bias Metrics

• Bayes Error Rate Estimation

• Bias Detection

• Cluster Assignment

• Coverage Analysis

• Dataset Cleaning

• Dataset Divergence

• Diversity Indices

• Drift Detection

• Duplicate Detection

• Label Parity Assessment

• Metadata

• Model Training Techniques

• Out of Distribution Detection

• Outliers Class

• Parity Assessment

• Statistical Analysis of Images

• Sufficiency of Datasets per Model

• Upperbound on Average Precision Estimation

For a quick reference of each algorithm’s functionality and requirements, see the Algorithm Overview page.

Algorithm Overview