Classification of Phishing Email Using Random Forest Machine Learning Technique

Algorithm 1

 Begin RF Algorithm

     Input: 𝑁: number of nodes

        𝑀: number of features

       𝐷: number of trees to be constructed

   Output: 𝑉: the class with the highest vote

    While stopping criteria is false do

    Randomly draw a bootstrap sample A from the training data 𝐷

    Use the steps below to construct tree 𝑇_𝑖 from the drawn bootstrapped sample A:

     (I)  Randomly select 𝑚 features from 𝑀; where 𝑚 ≪ 𝑀

     (II) For node d, calculate the best split point among the 𝑚 features

     (III) Split the node into two daughter nodes using the best split

     (IV) Repeat I, II and III until 𝑛 number of nodes has been reached

    Build your forest by repeating steps I–IV for 𝐷 number of times

    End While

    Output all the constructed trees 𝑇_𝑖1^𝐷

    Apply a new sample to each of the constructed trees starting from the root node

    Assign the sample to the class corresponding to the leaf node.

    Combine the decisions (or votes) of all the trees

    Output 𝑉, that is, the class with the highest vote.

 End RF Algorithm