What is the optimum number of steps we should take?
How do we decide this?
What is the optimum number of steps we should take?
hey @lintasheelkumar ,
There is no such rule with which you can get optimum number of steps to be taken.
It depends upon the data.
So , when you are done with feature engineering and just left with making a model.
Then you initially try some random steps manually , and get an idea of the range of steps to be taken that might be best for this model.
For example , your model works much better when number of steps are in range 100-130.
So now , you can perform grid search or simply create a loop that iterates from 100 to 130 and check what scores do you achieve on each iteration at validation data.
With this , you can get what value will be the most optimum for the current model .
I hope this helps.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.