A Theoretical Framework for Comparison of Data Mining Techniques

Main Article Content

Abhishek Taneja
R.K Chauhan

Abstract

In recent years data mining has become one of the most important tool for extracting, manipulating data and establishing patterns in
order to produce useful knowledge for decision making. Nearly all the worldly activities have ways to record the information but are
handicapped by not having the right tools to use this information to embark upon the fears of future. In data mining the choice of technique
depends upon the perceptive of the analyst. It is a daunting task to find out which data mining technique is suitable for what kind of underlying
dataset. In this process lot of time is wasted to find the best/suitable technique which best fits the underlying dataset. This paper proposes a
theoretical composition for comparison of different linear data mining techniques in a bid to find the best technique which saves lot of time
which is usually wasted in bagging, boosting, and meta-learning.

 

Keywords: Data mining, Factor Analysis, Multiple Linear Regression (MLR) , Partial Least Square (PLS), Ridge Regression.

Downloads

Download data is not yet available.

Article Details

Section
Articles