Date of Award
Culminating Project Type
Computer Science: M.S.
Computer Science and Information Technology
School of Science and Engineering
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Retention probabilities; predictive modeling; student retention; principal component analysis; Bayesian Networks; k-Nearest Neighbor; Random Forest;
Student graduation rates has always taken prominence in academic studies since it is considered a major factor to reflect the performance of any university. Accurate models for predicting student retention plays a major role is universities strategic planning and decision making. Students’ enrollment behavior and retention rate are also relevant factors in the measurement of the effectiveness of universities. This thesis provides a comparison of predictive models for predicting student retention at Saint Cloud State University. The models are trained and tested using a set of features reflecting the readiness of students for college education, their academic capacities, financial situation, and academic results during their freshman year. Principle Component Analysis (PCA) were used for feature selection. Six predictive models has been built. A comparison of the prediction results have been conducted using all features and selected features using PCA analysis.
Dissanayake, Hasith U., "Predicting Student Retention: A Comparative Study of Predictive Models for Predicting Student Retention at St. Cloud State University" (2016). Culminating Projects in Computer Science and Information Technology. 10.