Predicting Student Graduation in Higher Education Using Data Mining Models PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Predicting Student Graduation in Higher Education Using Data Mining Models PDF full book. Access full book title Predicting Student Graduation in Higher Education Using Data Mining Models by Dheeraj A. Raju. Download full books in PDF and EPUB format.
Author: Dheeraj A. Raju
Publisher:
ISBN:
Category : Electronic dissertations
Languages : en
Pages : 207
Get Book Here
Book Description
Predictive modeling using data mining methods for early identification of students at risk can be very beneficial in improving student graduation rates. The data driven decision planning using data mining techniques is an innovative methodology that can be utilized by universities. The goal of this research study was to compare data mining techniques in assessing student graduation rates at The University of Alabama. Data analyses were performed using two different datasets. The first dataset included pre-college variables and the second dataset included pre-college variables along with college (end of first semester) variables. Both pre-college and college datasets after performing a 10-fold cross-validation indicated no difference in misclassification rates between logistic regression, decision tree, neural network, and random forest models. The misclassification rate indicates the error in predicting the actual number who graduated. The model misclassification rates for the college dataset were around 7% lower than the model misclassification rates for the pre-college dataset. The decision tree model was chosen as the best data mining model based on its advantages over the other data mining models due to ease of interpretation and handling of missing data. Although pre-college variables provide good information about student graduation, adding first semester information to pre-college variables provided better prediction of student graduation. The decision tree model for the college dataset indicated first semester GPA, status, earned hours, and high school GPA as the most important variables. Of the 22,099 students who were full-time, first time entering freshmen from 1995 to 2005, 7,293 did not graduate (33%). Of the 7,293 who did not graduate, 2,845 students (39%) had first semester GPA
Author: Dheeraj A. Raju
Publisher:
ISBN:
Category : Electronic dissertations
Languages : en
Pages : 207
Get Book Here
Book Description
Predictive modeling using data mining methods for early identification of students at risk can be very beneficial in improving student graduation rates. The data driven decision planning using data mining techniques is an innovative methodology that can be utilized by universities. The goal of this research study was to compare data mining techniques in assessing student graduation rates at The University of Alabama. Data analyses were performed using two different datasets. The first dataset included pre-college variables and the second dataset included pre-college variables along with college (end of first semester) variables. Both pre-college and college datasets after performing a 10-fold cross-validation indicated no difference in misclassification rates between logistic regression, decision tree, neural network, and random forest models. The misclassification rate indicates the error in predicting the actual number who graduated. The model misclassification rates for the college dataset were around 7% lower than the model misclassification rates for the pre-college dataset. The decision tree model was chosen as the best data mining model based on its advantages over the other data mining models due to ease of interpretation and handling of missing data. Although pre-college variables provide good information about student graduation, adding first semester information to pre-college variables provided better prediction of student graduation. The decision tree model for the college dataset indicated first semester GPA, status, earned hours, and high school GPA as the most important variables. Of the 22,099 students who were full-time, first time entering freshmen from 1995 to 2005, 7,293 did not graduate (33%). Of the 7,293 who did not graduate, 2,845 students (39%) had first semester GPA
Author: Youssef Amr Naga
Publisher:
ISBN:
Category : Education
Languages : en
Pages : 0
Get Book Here
Book Description
Abstract: This thesis aims to propose and evaluate possible predictors of success for incoming university students to the American University in Cairo (AUC) who wish to enroll in its engineering programs, by considering their overallgrade point average (GPA) at graduation as the measure of their success (output variable). This study is composed of two phases. First, available university admission variables; i.e., gender, high school diploma, high school score, and proficiency level in the English language (the language of instruction at AUC) at the time of application are evaluated as a predictor of students' performance using five different data mining techniques. The analysis suggests that the current input admission variables can only predict student performance with limited accuracy. Moreover, of all the university admission data available, the type of high school diploma exhibits the greatest statistical significance as a predictor of student success in AUC engineering programs. The second phase of research was to conduct an analysis on thesix high school Diplomas that are typically offered in Egypt, and which regularly feed into AUC. This phase was conducted on 60 current high school students and aimed to identify component-wise cognitive traits and habits of mind that could correlate diploma type to predicted success in studying engineering in general. The research findings suggest that student scores on aptitude tests which directly measure engineering knowledge in high school are the best predictor of success for studying engineering at the university level, rather than the more widely recognized general cognitive ability scores (e.g., logical, and verbal abilities). Nevertheless, the findings also identified that when student preparedness isuniformly above-average across all these general cognitive abilities, that situation too is a good indicator of their success in studying engineering at the university level.
Author: Brenda Arndt Bailey
Publisher:
ISBN:
Category :
Languages : en
Pages : 470
Get Book Here
Book Description
Author: Sarah Alturki
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
Author: Michael S. Sims
Publisher:
ISBN: 9780438633759
Category : Forecasting
Languages : en
Pages : 77
Get Book Here
Book Description
Abstract: As a result of the California State Universities having four-year graduation rates among freshman students below 20% over the last few years, the Graduation Initiative 2025 has been deployed. This initiative aims to increase the graduation rates to 40%, while eliminating opportunity and achievement gaps. A signicant impact of this is looking at the success of rst-time-freshmen (FTF) and the prediction of whether or not they will graduate in a timely fashion. To this end, a natural [classification] problem is identied: amongst the FTF cohort who will graduate in four years or less(class instance = 1), or more than four years (class instance = 0) including students who did not graduate. In this paper, using Area Under the Curve (AUC) as our models performance metric, we construct classication models that quickly identify students at risk of not graduating in a timely fashion. Furthermore, we will construct models cumulatively—term by term—where each successive model includes student data from matriculation to the end of a given term. Using this approach allows a University to nd an optimal time to deploy possible intervention programs. It should be noted that optimal in this paper means, having a model with high AUC as early into the students academic career as possible. This way, an at-risk student is identied early, and the value of the University intervening is optimized. In this paper we will compare a variety of classication algorithms such as Logistic Regression, Random Forest, and XGBoost to see which model yields the highest AUC. Also we provide insight on interpretation specically identifying the eect each covariate has on the response. This approach will be unique because not only will it be a means for identifying the problem, but also serve as part of the solution.
Author: Dmitri Rogulkin
Publisher:
ISBN:
Category :
Languages : en
Pages : 7
Get Book Here
Book Description
The second year of college can be as important as the first year but far fewer studies have been conducted on second-year students. About 12% of students leave California State University - Fresno during or after their second year. In this report, we examined second year students to find the differences between those who graduate and those who leave. A decision tree data mining model was used to identify factors that predict students' graduation. A clustering model was used to classify 5 groups of students by multiple characteristics including their graduation rate (which ranges from 99% for one group to 14% for another). The findings showed that staying on track, which was defined as reaching sophomore level no later than the end of the third semester, and cumulative GPA after the first year were the most influential factors in predicting six-year graduation. Potential interventions that may benefit certain groups were suggested. (Contains 5 notes, 3 tables, and 1 figure.).
Author: Mohammed Alsuwaiket
Publisher:
ISBN:
Category :
Languages : en
Pages :
Get Book Here
Book Description
Author: Linsey Sledge Hugo
Publisher:
ISBN:
Category : College graduates
Languages : en
Pages :
Get Book Here
Book Description
As universities are increasingly held accountable for students career outcomes and as competition for jobs increases, institutions need to understand which students are more likely to be employed upon graduation and why. The purpose of this study is to determine to what extent undergraduate student academic and experience employability signals – including major, GPA, co-curricular activities, and internships – can predict if a student secures full-time employment prior to graduation. To predict employment prior to graduation, this research uses commonly recognized and advanced machine learning models, including logistic regression, discriminant analysis, decision trees, and neural networks.
Author: Ujwala Paladi
Publisher:
ISBN:
Category : College graduates
Languages : en
Pages : 190
Get Book Here
Book Description
The topic of this thesis is the analysis of factors influencing the retention of undergraduate level students at West Texas A&M University (WTAMU) with a special emphasis on STEM majors. The subjects of this study are first time college students, enrolled at WTAMU in Fall 2010, Fall 2011 and Fall 2012 that have a declared first major in a STEM field. Through Logistic regression analysis, factors influencing student retention and retention to graduation are identified. Identified factors that influence undergraduate student retention and graduation at WTAMU are math and science self-confidence, study habits, HSGPA, class percent, mothers' education, and senior year grades. Factors identified that influence retention to graduation of first year STEM majors at WTAMU are percentile of transfers, desire to finish, self-reported college prep activity, highest degree sought, sociability, distance from campus, HSGPA, class percent, Major code, fathers education, and work.
Author: David Kirp
Publisher: Oxford University Press
ISBN: 019086222X
Category : Education
Languages : en
Pages : 256
Get Book Here
Book Description
Higher education today faces a host of challenges, from quality to cost. But too little attention gets paid to a startling fact: four out of ten students -- that's more than ten percent of the entire population - -who start college drop out. The situation is particularly dire for black and Latino students, those from poor families, and those who are first in their families to attend college. In The College Dropout Scandal, David Kirp outlines the scale of the problem and shows that it's fixable - -we already have the tools to boost graduation rates and shrink the achievement gap. Many college administrators know what has to be done, but many of them are not doing the job - -the dropout rate hasn't decreased for decades. It's not elite schools like Harvard or Williams who are setting the example, but places like City University of New York and Long Beach State, which are doing the hard work to assure that more students have a better education and a diploma. As in his New York Times columns, Kirp relies on vivid, on-the-ground reporting, conversations with campus leaders, faculty and students, as well as cogent overviews of cutting-edge research to identify the institutional reforms--like using big data to quickly identify at-risk students and get them the support they need -- and the behavioral strategies -- from nudges to mindset changes - -that have been proven to work. Through engaging stories that shine a light on an underappreciated problem in colleges today, David Kirp's hopeful book will prompt colleges to make student success a top priority and push more students across the finish line, keeping their hopes of achieving the American Dream alive.
