Question
After spending several hours, you are now anxious to build a high accuracy model. As a result, you build 5 GBM models, thinking a boosting algorithm would do the magic. Unfortunately, neither of models could perform better than benchmark score. Finally, you decided to combine those models. Though, ensembled models are known to return high accuracy, but you are unfortunate. Where did you miss?
Answers
As we know, ensemble learners are based on the idea of combining weak learners to create strong learners. But, these learners provide superior result when the combined models are uncorrelated. Since, we have used 5 GBM models and got no accuracy improvement, suggests that the models are correlated. The problem with correlated models is, all the models provide same information.
For example: If model 1 has classified User1122 as 1, there are high chances model 2 and model 3 would have done the same, even if its actual value is 0. Therefore, ensemble learners are built on the premise of combining weak uncorrelated models to obtain better predictions.
    Your Comment




  • Contributors: *,


Search
Can you Answer!!
  • Q Ibn-e-Batuta by birth was a:
  • Q How to attach the ClearQuest database to your project?
  • Q What are various IDs associated with a process?
  • Q Explain MRP type
  • Q What is the difference between cathode ray and beta ray?
  • Q A cannon ball is fired. The motion of this ball is an example of
  • Q Best piece of advice you would give a home enthusiast?
  • Q What is controls and what are different types of controls in AWT?
  • Q Define the syntax of xpointer
  • Q Group of Monuments at Pattakakal is in
  • Q How can the principles be applied to the enterprise?