• Entry
  • Reader's guide
  • Entries A-Z
  • Subject index

Cross-validation is a data-dependent method for estimating the prediction error of a fitted model or a trained algorithm. The basic idea is to divide the available data into two parts, called training data and testing data, respectively. The training data are ...

Loading
  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles