Nearest Neighbor


  • A Supervised Learning Algorithm in which a new Document is Classified by finding the most similar Document in the Training Set, and assuming that the correct Coding for the new Document is the same as the most similar one in the Training Set. 1
  • A statistical procedure that classifies objects, such as documents, according to the most similar item that has already been assigned a category label. This approach uses a set of labeled examples to classify subsequent unlabeled items, by choosing the category assigned to the most similar labeled example (its nearest neighbor) or examples. K-nearest neighbor classification uses the k most similar classified objects to determine the classification of an unknown object. 2


  1. Maura R. Grossman and Gordon V. Cormack, EDRM page & The Grossman-Cormack Glossary of Technology-Assisted Review, with Foreword by John M. Facciola, U.S. Magistrate Judge2013 Fed. Cts. L. Rev. 7 (January 2013).
  2. Herb Roitblat, Predictive Coding Glossary.