Intro to Predictive Coding: Overview & Interpretation of Terminology June 2014 | Page 30

Glossary
Random sampling—the statistical process of
choosing objects randomly, meaning that each
object has an equal chance of being selected.
Random sampling can be used to train predictive
coding systems and to evaluate their efficacy.
Recall –the proportion of responsive documents in
the entire collection that have been retrieved.
Relevance feedback—a class of machine learning
techniques where users indicate the relevance of
items that have been retrieved for them and the
machine learns thereby to improve the quality of its
recommendations.
Richness – the proportion of responsive documents
in a collection.
Sampling – the process of selecting a subset of
items from a population and inferring from the
characteristics of the sample what the characteristics of the population are likely to be.