In the random forest, how many decision trees do we need to use to get a good result
Random Forest builds multiple decision trees and merges them together to get a more accurate and stable prediction.
Random forest is an ensemble method where we use lots of Decision Trees. Now the catch is the more number of trees the more samples we are creating for our data, and the more samples we have created the more we reduced the bias-ness of our data.
But at a certain point, the cost of collecting a larger sample will be higher than the benefit in accuracy obtained from such a larger sample. and there would be a time comes when we would be creating enough samples and now data is getting duplicated, I mean the same data points are coming in different samples, this can be normal data or can be outliers also which are coming in different samples. This will increase the bias-ness of our results.
So if we want we can find out the standard n_estimators using the grid/random search method. In this, we will be able to find out the number of better decision trees for our good result.