Interview question: What do you understand by Random Forest?

In an early blog post I asked the interview question: ‘What do you understand by decision tree?’. That particular blog post can be found here:- https://medium.com/@tracyrenee61/interview-question-what-do-you-understand-by-decision-tree-f78ce8f6fbed

In this blog post I ask the interview question: ‘What do you understand by random forest?’.

Before one can understand the random forest algorithm, he must first understand the decision tree. The reason for this is because the random forest is simply a collection of decision trees that are averaged or majority voted to come up with a prediction.

Random forest algorithms have three main hyperparameters that need to be set before training. These include node size, the number of trees, and the number of features sampled.

The key benefits of the random forest algorithm are:-

1. Reduced risk of overfitting,
2. Flexibility to handle both regression and classification problems, and
3. Ease of determining feature importance.

The challenges of the random forest algorithm are:-

1. It is time consuming to train the data,
2. It requires larger datasets and memory allocations, and