Random Forest Algorithm(05!05!14)

PowerPoint Presentation

Dynamic Pruning of Random Forest

Under the esteemed supervision of Mrs. Nagarjuna Devi

Y. Poorna DurgaP. Saimadhu Team members:Dynamic Pruning of Random Forest Classifier

IntroductionExisted MethodsProposed MethodRequirements analysisImplementation Results

Introduction

Random forest overviewRandom forest AlgorithmApplications of Random Forest Classifier

Existed Methods

Static Pruning Methods Methods based on diversity measures. Methods based on search algorithms.Methods based on clustering of classifiers.Methods based on heuristic rules.

Proposed Method

Dynamic pruning

Requirements analysisProgramming Languages : PythonPackages Required : NumPyTools : Weka IDE : Stani's Python Editor(SPE)Data sets : Titanic, Qualitative Bankruptcy , Cancer detection , USA voting ImplementationInformation Gain module Decision Tree moduleRandom Forest module( Including proposed method)ResultsCancer Detection with 10 attributes including target attribute Weka accuracy average of 10 results : 70.04 %Proposed method average of 10 results : 74.20 %ResultsQualitative Bankruptcy with 7 attributes including target attribute Weka accuracy average of 10 results : 92.04 %Proposed method average of 10 results : 95.32 %ResultsTime Complexity : For building a tree is O(mnlogn)Time Complexity : For building M trees O(M(mnlogn)Where :M : Number of trees.m : Number of attributes.n : The number of instances in the training data. Thank you