Filter Method

The filter feature selection methods make use of statistical techniques to predict the relationship between each independent input variable and the output (target) variable. Which uses it to assigns scores for each feature. Later the scores are used to filter out those input variables/features that we will use in Feature Selection of the model.


Notes:

  • Filter method is computationally inexpensive. but less than other feature selection methods.
  • It Requires lot’s of high dimensional data for acceptable results.
  • It's not prone to Overfitting.
  • Unlike Wrapper Method, Filter method doesn't incorporate a specific algorithm in the process.