Degree Type
Honors Capstone Project
Date of Submission
Spring 5-1-2018
Capstone Advisor
Leonid Kovalev
Capstone Major
Mathematics
Capstone College
Arts and Science
Audio/Visual Component
no
Capstone Prize Winner
no
Won Capstone Funding
no
Honors Categories
Sciences and Engineering
Subject Categories
Algebra | Mathematics | Physical Sciences and Mathematics
Abstract
Nowadays, data is playing a bigger part than ever before in the history. In order to get more useful information, methods involving matrix are powerful. There are different algorithms that are able to help one to learn the information they need from data. In this study, there are two main algorithms that I will focus on. One is Pagerank algorithm, a traditional algorithm that was applied to searching engine decades ago in Google. However, Pagerank algorithm has certain limits in providing information like covariance between different factors. Thus, another method is also studied, which is principal component analysis (PCA), while there are also weak points of PCA in the study, such as missing data and this paper will provide five potential solutions to such problem. In this study, my data base is 37 students’ grades on 13 different math courses and based on the information from this data pool, advisors are able to give better advice to their students.
Recommended Citation
Yu, Kaiye, "Matrix Methods of Data Analysis" (2018). Renée Crown University Honors Thesis Projects - All. 1160.
https://surface.syr.edu/honors_capstone/1160
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
