Posts tagged with: random forests

Randomness and RandomForests

One of the enhancing use case of randomness subjected to machine learning is Random Forests. If you are familiar with Decision Tree that is used inasmuch as vast amount of data analysis and machine learning problems, Random Forests is simple to grasp.

For the beginners, decision tree is a simple, deterministic data structure for modelling decision rules for a specific classification problem (Theoretically shortest possible message length in Information jargon). At each node, one feature is selected to make instance separating decision. That is, we select the feature that separates instances to classes with the best possible “purity”. This “purity” is measured by  entropy, gini index or information gain. As lowing to the leaves , tree is branching to disperse the different class of instance to different root to leaf paths.  Therefore, at the leaves of the tree we are able to classify the items to the classes. Continue Reading


What is different between Random Forests and Gradient Boosted Trees?

This a simple confusion for especially beginners or the practitioners of Machine Learning. Therefore, here I share a little space to talk about Random Forests and Gradient Boosted Trees.
To begin with, divide the perspective of differences in to two as algorithmic and practical.
Algorithmic difference is; Random Forests are trained with random sample of data (even more randomized cases available like feature randomization) and it trusts randomization to have better generalization performance on out of train set.
On the other spectrum, Gradient Boosted Trees algorithm additionally tries to find optimal linear combination of trees (assume final model is the weighted sum of predictions of individual trees) in relation to given train data. This extra tuning might be deemed as the difference. Note that, there are many variations of those algorithms as well.
At the practical side; owing to this tuning stage, Gradient Boosted Trees are more susceptible to jiggling data. This final stage makes GBT more likely to overfit therefore if the test cases are inclined to be so verbose compared to train cases this algorithm starts lacking. On the contrary, Random Forests are better to strain on overfitting although it is lacking on the other way around.
So the best choice depends to the case your have as always.