Random Forest

The random forest is one of the most popular and most powerful supervised machine learning algorithm. That is capable of performing both regression and classification tasks. In general the more trees in the forest the more robust the prediction and thus higher accuracy to model multiple decision  trees to create the forest.

Build up multiple decision tree using algorithm such as 

• Information gain
• GIGI index approach 
• Other decision tree algorithms

Advantages:
Here are some advantages of using random forests.

1. Both classification and the regression task
2. Handle the missing values and maintains the accuracy for missing data
3. Will not over-fit the model 
4. Handle large data set with higher dimensionality. 

Disadvantage:

1. Good job at classification but as good as regression 
2. Very little control one what the model does 

Application of Random forest:

It use in banking sectors so these are for finding loyal customers and finding the fraud customers. It can be used in medicine where we identified the correct combination of components to validate medicine. Random forest algorithm also help for identifying disease by analysis the patient'a medical records. In stoke market random forest identify the stoke behavior. In computer vision it used for image classifications. Microsoft has used random forest for body passed classifications. For x box kinect and others applications involved lip-reading as well as voice classifications. 

Random Forest Pesudo code:

•  Assume number of cases in the training is N. Then sample of this N cases is taken at random but with replacement
• If there are M input variables, a number m<M is specified such as that at each node, m variables are selected at random out of the M. The best split on this m is used to split the node.The value of m is held constant while we go the forest.
• Each tree is grown the largest extent possible and there is no pruning. 
• Predict new data by aggregating the predictions of the n tree