Date of Award
Fall 12-2015
Document Type
Thesis
Degree Name
M.S. Computer Science
Department
Computer Science and Information Technology
First Advisor
Dr. Lisa Frye
Abstract
This project will encompass an in-depth study of at-risk college students that implements both predictive analysis and data mining techniques. At-risk students are students with a specific set of demographics, study habits, and historical academic performance. Using predictive analysis, factors that directly correlate with student performance will be used to create a detection algorithm for particular student characteristics. From this data, it will be determined if a student is deemed “at-risk” academically, and if action needs to be taken by faculty or the student themselves.
The goal of this study is to determine the optimal algorithm that identifies at-risk students at Kutztown University, and apply that algorithm to a web-based analysis tool. This web application would be accessed by students and faculty to view their (or their students’) progress academically. Various “early-alert” systems were researched and analyzed to identify the type of system suitable for use at Kutztown University.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Cresse, Nicole Alaine, "An Investigation of At-Risk College Students Through Data Mining and Implementation of Predictive Analysis" (2015). Kutztown University Masters Theses. 3.
https://research.library.kutztown.edu/masterstheses/3
Included in
Academic Advising Commons, Data Science Commons, Higher Education Commons, Numerical Analysis and Scientific Computing Commons
