Rank Prediction Using Principal Component Analysis

Abstract

"Rank Prediction Using Feature Selection and Transformation Techniques" seeks to establish the rankings of various countries based on their national security and to rank players from the Indian Premier League (IPL). This is achieved through the implementation Principal Component Analysis (PCA). Principal Component Analysis (PCA) is a classical multivariate data dimensionality reductiondata preprocessing, compression and visualization method suitable for many applications in biology, social sciences and engineering. A limitation of PCA is the lack of interpretation due to nonzero loading and inconsistencies in highdimensional elements. Principal component analysis (sparse PCA) mainly aims to solve the above problems of PCA. In the last few years, many studies have been prepared on the development and theoretical analysis of sparse principal component analysis. The aim of this article is to conduct a literature review on the latest developments in highdimensional sparse principal component analysis from the perspective of algorithms and statistical theory. We first provide an overview of PCA and sparse PCA. Secondly, different PCA algorithms are divided into several categories, the structures and methods in each category are explained in detail, and the sparse PCA package is given. Considering that the variance of PCA increases with the increase of the index value, the theoretical analysis of sparse PCA was analysed.