5.11.5. Support Vector Machine (clip0243 action)

<< Click to Display Table of Contents >>

Navigation:  5. Detailed description of the Actions > 5.11. R Predictive >

5.11.5. Support Vector Machine (clip0243 action)

 
Icon: ANATEL~4_img18  

 

Property window:

 

ANATEL~4_img17

 

Short description:

Create a SVM model

 

Long Description:

Create a predictive model based on “Support Vector Machine” (SVM).

 

SVM models are interesting from a purely theoretical point-of-view because they have mathematical properties that allows researcher to write many scholary articles about them.

 

 

The SVM algorithm is included in Anatella mainly because of historical reasons (and for explanatory/teaching purposes). Indeed, from a pratical point-of-view, SVM are not very useful anymore because:
 

The SVM algorithm do not scale well: it crashes (typically because of RAM memory issues) on most common-size datasets

The SVM algorithm is extremely Slow (several orders of magnitude slower than any other algorithm)

Compared to other modeling algorithms, the SVM algorithm is not very accurate (other algorithms have typically higher AUC, and higher accuracy). This fact is visible in all datamining competitions (KDD cups, Kaggle) where SVM always ranks amongst the worst algorithms.