Support vector regression (SVR) is a machine learning method for fitting sampled observations to a function, and using it to predict unseen data. In InformationRetrieval, it is widely applied in many fields, such as document clustering, Query Performance Prediction and other applications.
A more comprehensive introduction to the support vector regression can be found in:
A.J. Smola and B. Schölkopf. A tutorial on Support Vector Regression. In Statistics and Computing 14: 199-222. 2004.