Encyclopedia of Database Systems

2018 Edition
| Editors: Ling Liu, M. Tamer Özsu

Support Vector Machine

  • Hwanjo YuEmail author
Reference work entry
DOI: https://doi.org/10.1007/978-1-4614-8265-9_557




Support vector machines (SVMs) represent a set of supervised learning techniques that create a function from training data. The training data usually consist of pairs of input objects (typically vectors) and desired outputs. The learned function can be used to predict the output of a new object. SVMs are typically used for classification where the function outputs one of finite classes. SVMs are also used for regression and preference learning, for which they are called support vector regression (SVR) and ranking SVM, respectively. SVMs belong to a family of generalized linear classifier where the classification (or boundary) function is a hyperplane in the feature space. Two special properties of SVMs are that SVMs achieve (i) high generalization (Generalization denotes the performance of the learned function on testing data or “unseen” data that are excluded in training.) by maximizing the margin (Margin denotes the distance between the hyperplane and the...

This is a preview of subscription content, log in to check access.

Recommended Reading

  1. 1.
    Burges CJC. A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc. 1998;2(2):121–67.CrossRefGoogle Scholar
  2. 2.
    Hastie T, Tibshirani R. Classification by pairwise coupling. Adv Neural Inf Proces Syst. 1998;10:507.zbMATHGoogle Scholar
  3. 3.
    Herbrich R, Graepel T, Obermayer K, editors. Large margin rank boundaries for ordinal regression. Cambridge, MA: MIT Press; 2000.Google Scholar
  4. 4.
    Smola AJ, Scholkopf B. A tutorial on support vector regression. Technical report, NeuroCOLT2 technical report NC2-TR-1998-030. 1998.Google Scholar
  5. 5.
    Yu H. SVM selective sampling for ranking with application to data retrieval. In: Proceedings of the 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2005.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of IowaIowa CityUSA

Section editors and affiliations

  • Kyuseok Shim
    • 1
  1. 1.School of Elec. Eng. and Computer ScienceSeoul National Univ.SeoulRepublic of Korea