Random forest

Today I will be talking about a technique called random forest. A random forest constructs a number of decision trees on the same training data.

The trees built with random forest randomly select which variable to do the first split. For classification the output of a random forest is the model with the most amount of classification votes out of all the trees while for regression the output of a random forest is the mean prediction of the individual trees.

Continue reading Random forest

Decision trees implementation

For my first post I would like to show a learning tool that is a decision tree using ctree()  and how it can be implemented in R. I will be covering the general idea of what is a decision tree and provide some examples using Iris data set which can be found at UCI Machine Learning Repository.

After the concept of a decision tree is explained, for the next post I will delve a little further and talk about random forest and how it works with decision trees.

Continue reading Decision trees implementation