Enrollment management: Development of prediction model based on logistic regression
TL;DR: In this paper, a model for forecasting and decision-making by applying logistic regression was developed to predict professional choices of graduates after finishing vocational school, which can predict the number and structure of students enrolled in higher education.
Abstract: This paper presents the development of a model for forecasting and decision-making by applying logistic regression. The prediction of professional choices for graduates has been verified on the sample of 159 graduates. Predictor variables are grouped in nine input variables and the data collected from the Unique Education Information System database. Professional choices of graduates after finishing vocational school are grouped into three output variables and the data collected in the survey. The obtained results show that the application of logistic regression can predict the number and structure of students enrolled in higher education.
Citations
More filters
TL;DR: In this paper, the authors studied the urban growth pattern in five major cities in the Middle East and North Africa (MENA) region including Dubai (United Arab Emirates), Cairo (Egypt), Doha (Qatar), Casablanca (Morocco), and Riyadh (Kingdom of Saudi Arabia).
13 citations
TL;DR: A novel methodology for urban growth prediction using a machine learning approach that treats successive historical satellite images of an urban area as a video for which future frames are predicted, which adopts a time‐dependent convolutional encoder–decoder architecture.
Abstract: This paper presents a novel methodology for urban growth prediction using a machine learning approach. The methodology treats successive historical satellite images of an urban area as a v...
10 citations
TL;DR: An enrollment management model by applying artificial neural network (ANN) is presented to show that ANNs are more successful in predicting than the classical statistical method – regression analysis (logistic regression).
Abstract: This paper presents an enrollment management model by applying artificial neural network (ANN). The aim of the research, which has been presented in this paper, is to show that ANNs are more succes...
4 citations
Cites background from "Enrollment management: Development ..."
...…point out that the development of different prediction models, optimization models, and decision-making (Camarena-Alvarado 2010; Chang 2006; Gerasimovic, Bugaric, and Bozic 2016; Gerasimovic et al. 2011; Herzog 2006; Thanh and Haddawy 2007; Wook et al. 2009) has been successfully solved,…...
[...]
01 Jan 2021
TL;DR: This chapter aims to introduce a machine learning model to predict the outcomes in a smart education system.
Abstract: A smart education system uses emerging technologies and generates a vast amount of heterogeneous data in the learning environment. The conventional methods presently used by the educational administrators for decision-making are minimal and take more time to generate the results. The educational administrators could not be able to predict the results quickly and advance for better decision-making. Today, artificial intelligence approaches are widely used in educational systems for automating educational processes. These approaches achieve a better, efficient, and effective modern education system. Integrating machine learning deep learning techniques with a smart education system can automatically analyze the generated data for better decision-making and provide recommendations to students and educational administrators. This chapter aims to introduce a machine learning model to predict the outcomes in a smart education system.
1 citations
TL;DR: Results have revealed that gender, scholarship, province, location, and division are significant factors and contributing in predicting students' retention at VU.
Abstract: Due to the of use of ICTs and ODL, Virtual University (VU) has become one of leading distance learning university in Pakistan. However, the retention rate among online learners found considerably low. The primary objective of this research was to dig out determinants of retention of MS /MPhil students at VU and modeling their retention by considering important influences. For sampling purpose, three departments with the most students were considered and complete enumeration was done. There were 4,608 students from three departments; Computer Science & Technology, Management Sciences and Education have been included in this study. To dig out the important retention factors, this research has used a Chi-Square test, optimal scaling, a decision tree using CHAID analysis, and then developed a suitable model for student retention. Binary logistic regression techniques were applied. Results have revealed that gender, scholarship, province, location, and division are significant factors and contributing in predicting students' retention at VU. Detailed outputs are shown in respective tables and figures. At the end, different recommendations and suggestions are proposed.
References
More filters
Book•
01 Jan 1968
1,360 citations
"Enrollment management: Development ..." refers methods in this paper
...The characteristic of the method of regression analysis is that the dependent variable, namely the forecasting value, is expressed as a mathematical function of one or more variables, predictive values, known in the time of forecasting (Hillier & Lieberman, 2001)....
[...]
TL;DR: The authors used the High School and Beyond Sophomore cohort, the high school Class of 1982, to analyze the effects of the amount of tuition charged and aid offered on student enrollment decisions.
Abstract: Most research on student price response was conducted on students who entered college before the Pell Grant program was implemented in fall 1973. This study uses the High School and Beyond Sophomore cohort, the High School Class of 1982, to analyze the effects of the amount of tuition charged and aid offered on student enrollment decisions. The findings include (1) all forms of financial aid—grants, work, and loans—were effective in promoting enrollment; (2) one hundred dollars of aid (any type) had a stronger influence on enrollment than a one-hundred-dollar reduction in tuition; (3) low-income students were more responsive to increases in grant aid than to increases in loans or work study; and (4) high-income students were not responsive to changes in aid amounts.
224 citations
"Enrollment management: Development ..." refers background in this paper
...Coding Variable Category Frequency (1) (2) (3) (4) (5)...
[...]
...9,3 9,4 9,5 41,737 42, 233 39,700 c c c + ⋅ + ⋅ + ⋅ (4)...
[...]
...improvement in performance in the final year for one unit (sufficient (2), good (3), very good (4), excellent (5)) increases the probability of enrollment in FME about 5 times....
[...]
Book•
01 Nov 1984
167 citations
"Enrollment management: Development ..." refers background in this paper
...…predicting the professional choice of graduate students, (Gerasimovic et al., 2011; Miljkovic et al., 2011), selection and retention of students (Hossler, 1984), the role of financial support for students (Spaulding & Olswang, 2005), enrollment management strategies (Antons & Maltz, 2006;…...
[...]
TL;DR: In this paper, the authors use regression and path analysis to predict student retention and time to degree completion of a typical student in higher education, and identify who is at risk of dropping out or who is likely to take a long time to graduate.
Abstract: Understanding student enrollment behavior is a central focus of institutional research in higher education. However, in the eyes of an enrollment management professional, the capacity to explain why students drop out, why they transfer out, or why some graduate quickly while others take their time may be less critical than the ability to accurately predict such events. Being able to identify who is at risk of dropping out or who is likely to take a long time to graduate helps target intervention programs to where they are needed most and offers ways to improve enrollment, graduation rate, and precision of tuition revenue forecasts. Explanatory models by regression and path analysis have contributed substantially to our understanding of student retention (Adam and Gaither, 2005; Pascarella and Terenzini, 2005; Braxton, 2000), although the cumulative research on time to degree (TTD) completion is less impressive. A likely explanation for this is the more complex nature of the path to graduation, which has lengthened considerably over the past thirty years for a typical student (Knight, 2002, 2004; Noxel and Katunich, 1998; Council for Education Policy, Research and Improvement, 2002). Thus, whereas
140 citations
TL;DR: Data-mining technology's predictive modeling was applied to enhance the prediction of enrollment behaviors of admitted applicants at a large state university.
Abstract: Data-mining technology's predictive modeling was applied to enhance the prediction of enrollment behaviors of admitted applicants at a large state university.
48 citations
"Enrollment management: Development ..." refers background or methods in this paper
...Coding Variable Category Frequency (1) (2) (3) (4) (5)...
[...]
...The logistic regression equation (3) of the analyzed model is:...
[...]
...improvement in performance in the final year for one unit (sufficient (2), good (3), very good (4), excellent (5)) increases the probability of enrollment in FME about 5 times....
[...]
...…in the field of prediction and decision making in the process of enrollment management, indicates that developing different forecasting, optimization and decision making models, among other is prepared by application of regression analysis, i.e. logistic regression (Chang, 2006; Edward, 1990)....
[...]