Student Graduation Rates Research Articles

Implementation of Neural Network Algorithms in Predicting Student Graduation Rates

Higher education institutions are required to be providers of quality education. One of the instruments used by the government to measure the quality of education providers is the number of graduates. The higher the graduation rate, the better the quality of education and this good quality will positively affect the accreditation value given by BAN-PT. Therefore, in this study, researchers provide input for research conducted at Bhayangkara University, Greater Jakarta to predict student graduation rates using the Neural Network algorithm. Neural Network is a method in machine learning developed from Multi Layer Perceptron (MLP) which is designed to process two-dimensional data. Neural Network is included in the type of Deep Neural Network because of the depth of the network level and is widely implemented in image data. Neural Network has two methods; namely classification using feedforward and learning stages using backpropagation. The way Neural Network works is similar to MLP but in Neural Network each neuron is represented in two dimensions, unlike MLP where each neuron is only one dimension. The prediction accuracy obtained is 98.27%. unlike MLP where each neuron is only one-dimensional. The prediction accuracy obtained is 98.27%. unlike MLP where each neuron is only one-dimensional. The prediction accuracy obtained is 98.27%.

Data‐driven decision‐making model based on artificial intelligence in higher education system of colleges and universities

AbstractThe quality of management decisions is one of the main issues facing higher education institutions today. Strategic decisions taken by the higher education institutions affect policies, schemes, and actions that the institutions are considering. Machine learning is an emergent artificial intelligence field that utilizes different algorithms, analyses data, and delivers a better understanding of the data contained in a specific context. Hence, in this paper, data‐driven decision‐making model has been proposed based on artificial intelligence in colleges and universities. Student data, graduation rate and curriculum design have been analysed for administrative decision‐making in college or university based on the machine learning method. With the availability of huge quantities and high‐quality input training data, machine‐learning progressions can attain precise outcomes and enable informed decision‐making. The experimental findings show that the suggested model improves the outcome ratio of 90.72%, the performance ratio of 97.62%, prediction ratio of 96.35%, decision‐making level of 95.51%, accuracy ratio of 95.61%, an efficiency ratio of 98.14%, graduation rate of 85.86%, data security rate (95.61%) and error rate 33.21% compared to other methods.

PROFILING BACHELOR OF SCIENCE IN STATISTICS (BSS) STUDENTS UNDER THE OPEN ENROLMENT POLICY

This study established a profile of Bachelor of Science in Statistics (BSS) students under the open enrolment policy of Visayas State University (VSU). The study also determined the graduation rate of the BSS students. Data on the present BSS students were collected from a survey of currently enrolled students while data on the past BSS students were taken from the previous study. Data used to track down the BSS students since their first year to determine the graduation rate of each batch covered and were taken from the Office of the University Registrar. Results showed that majority of the present BSS students are female. All BSS students surveyed come from the Visayas area with most of them come from Region VIII, Philippines. While most of the BSS students have annual family incomes below the poverty line in Region VIII, still most of them get their financial support from their parents only. Majority are regular students and want to work as statisticians in the future. The relative importance of factors influencing the choice of degree program are very similar between the past and the present BSS students. The graduation rate of BSS students is variable (coefficient of variation of 42.5%) with a median of 26.1% and a mean of 25.3%. Hence, an extensive recruitment and orientation about the program must be done to increase the enrollees and develop their interest towards the program, respectively.

Academic Advising and International Collaboration Agreements

The purpose of this quantitative study was to examine and compare the retention and graduation rates of students in a doctoral program in Education that holds collaboration agreements with institutions in Colombia, Mexico, and the Dominican Republic. Results reveal that the number of years to graduate from the program averaged 7.7 years. Seventy-five percent of the participants from Colombia graduated within four years, whereas 75% of participants in the Dominican Republic graduated within 6.7 years. Findings also highlight the importance of program support from academic advising personnel to assist doctoral students in completing their degrees on time.

Athletic Training Educators' ConferenceApril 29–May 1, 2021

Athletic Training Educators' ConferenceApril 29–May 1, 2021

EDUCATION GAME MATH MENGGUNAKAN ALGORITMA FUZZY SUGENO

The quality of education is very important for success in learning, by using various methods or tools to make it easier for students to understand discrete mathematics material, based on the 23% graduation rate of students who do not complete discrete mathematics at XYZ University, it is necessary to innovate learning applications, use The game education application provides convenience in developing learning media, namely the Digital Math Game, an Android-based mobile application that makes it easy for students to learn discrete mathematics. This application is equipped with several features, namely games to hone the extent to which students' ability to do discrete math exercises randomly, with the reward in the game, the questions are designed to be more difficult and graded, Fuzzy Sugeno algorithm calculates logic to determine rewards based on time variables and problem solving. This application has an AR (Augmented Reality) feature to provide 3D views and videos on discrete mathematics textbooks, 30 algorithm testing with 100% accuracy.

Analisis Metode K-Nearest Neighbors (K-NN) Dan Naive Bayes Dalam Memprediksi Kelulusan Mahasiswa

In this research the author aims to apply the K-NN and Naive Bayes algorithms for predicting student graduation rates at Sekolah Tinggi Pariwisata (STP) Mataram, The comparison of these two methods was carried out because based on several previous studies it was found that K-NN and Naive Bayes are well-known classification methods with a good level of accuracy. But which one has a better accuracy rate than the two algorithms, that's what researchers are trying to do. The output of this application is in the form of information on the prediction of student graduation, whether to graduate on time or not on time. The selection of STP as the research location was carried out because of the imbalance between the entry and exit of students who had completed their studies. Students who enter have a large number, but students who graduate on time according to the provisions are far very small, resulting in accumulation of the high number of students in each period of graduation, so it takes the initial predictions to quickly overcome these problems. Based on the results of designing, implementing, testing, and testing the Student Graduation Prediction Application program using the K-NN and Naive Bayes Methods with the Cross Validation method, the result is an accuracy for the K-NN method of 96.18% and for the Naive Bayes method an accuracy of 91.94% with using the RapideMiner accuracy test. So based on the results of the two tests between the K-NN and Naive Bayes methods which produce the highest accuracy, namely the K-NN method with an accuracy of 96.18%. So it can be concluded that the K-NN method is more feasible to use to predict student graduation

Pengembangan Model Untuk Prediksi Tingkat Kelulusan Mahasiswa Tepat Waktu dengan Metode Naïve Bayes

Many parameters affect the timeliness of student graduation, starting from the student's interest in certain majors, the type of class chosen, to the grades for each semester obtained. This is a determining factor in how students can graduate on time or not at the end of their education. So a model is needed to predict student graduation rates on time, using alumni data whose data is obtained from several universities in Palembang City. The model used is a Naïve Bayes algorithm which serves as a model for classification. The dataset used is alumni data that has been collected from several universities, while the attributes used are the Department, College, Class Type, Temporary IP Value from semester 1 to 4, graduation year, and college generation. Then from the attributes and models used, the researcher used the Python 3 programming language and the Jupyter Notebook tools to process the prepared dataset. Furthermore, the distribution of the dataset is divided by 70% for training data and 30% for testing data. To test the algorithmic process used by researchers using K-Fold Validation. The results of this study are the accuracy of the prediction model carried out, where the accuracy results obtained from the Python 3 programming language and the Naïve Bayes algorithm are 0.8103.

EFFECT OF COGNITIVE CRAFTING ON GRADUATION RATE OF STUDENTS IN FEDERAL UNIVERSITIES, SOUTH EAST, NIGERIA

The study investigated the effect of cognitive crafting on the graduation rate of students in Federal Universities, South East, Nigeria. The study is anchored on Elgar’s Performance Theory of organizations. The survey research method was adopted for the study, making use of structured questionnaire as instruments for data collection. Data were collected from both primary and secondary sources. Hypotheses were tested using the simple linear regression. The study found that cognitive crafting had significant positive effect on the graduation rate of students in Federal Universities, South East, Nigeria (r 0.803; P < 0.05). It was therefore, concluded that cognitive capabilities which promote students’ graduation rate enhances the overall performance of Universities in South East, Nigeria. The study recommended that Universities should be properly funded to encourage the employment and retention of professionals with cognitive capabilities that would enhance students’ graduation rate and overall performance of the Universities.
 
 JEL: B10; A02; C06
 
 <p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/edu_01/0770/a.php" alt="Hit counter" /></p>

How to Promote Diversity and Inclusion in Educational Settings: Behavior Change, Climate Surveys, and Effective Pro-Diversity Initiatives

We review recent developments in the literature on diversity and inclusion in higher education settings. Diversity interventions increasingly focus on changing behaviors rather than mental constructs such as bias or attitudes. Additionally, there is now a greater emphasis on the evaluation of initiatives aimed at creating an inclusive climate. When trying to design an intervention to change behavior, it is advised to focus on a segment of the population (the “target audience”), to try to get people to adopt a small number of specific new behaviors (the “target behaviors”), and to address in the intervention the factors that affect the likelihood that members of the target audience will engage in the new target behaviors (the “barriers and benefits”). We report our recent work developing a climate survey that allows researchers and practitioners to identify these elements in a particular department or college. We then describe recent inclusion initiatives that have been shown to be effective in rigorous empirical studies. Taken together this paper shows that by implementing techniques based on research in the behavioral sciences it is possible to increase the sense of belonging, the success, and the graduation rate of minority students in STEM.

Implementing a Hybrid Summer Transition Program

The mission of the Virginia Commonwealth University Louis Stokes Alliance for Minority Participation (VCU LSAMP) program is to increase the retention and graduation rates of students from underrepresented racial and ethnic groups in science, technology, engineering, and mathematics (STEM) majors and those who matriculate into graduate programs. VCU LSAMP offers a hybrid summer transition program (HSTP) focused on facilitating the high school to college and two-year to four-year college transition process for students majoring in STEM disciplines. The goals of the program are to 1) build community among a cohort of students, 2) orient students to VCU, 3) prepare students for the academic rigors of their first year in a STEM discipline at VCU, 4) expose students to opportunities and careers in STEM, 5) engage them in the VCU LSAMP program, and 6) provide financial support. Five distinct components of the VCU HSTP are 1) a six-week online summer component, 2) a 1 week on-campus orientation, 3) a Design Project Challenge, 4) a transfer student track, and 5) an academic year component. Evaluation data reveals that the HSTP assisted participants with adjustment to the college schedule and setting, facilitated the formation of study groups, and increased overall motivation to graduate. The online courses helped familiarize students with both the academic topics in their chemistry and mathematics classes and the behaviors and norms of STEM majors. On average, participants in the HSTP had higher retention (85%) and graduation (73%) rates when compared with their peers (81% and 64%, respectively). Furthermore, those students who complete the online classes’ requirements had a higher probability of receiving a grade of B or better in their first mathematics or chemistry class.

APRIORI ALGORITHM FOR FINDING RELATIONSHIPS BETWEEN STUDENT SELECTION PATHWAYS SCHOOL DEPARTMENTS WITH STUDENT GRADUATION LEVELS

The selection process for New Student Admissions (PMB) of State Islamic Universities in Indonesia, especially at UIN Raden Intan Lampung for undergraduate (S1) programs, is pursued through 3 (three) different selection patterns. Selection of SPAN-PTKIN, UM-PTKIN, and UM independent. The three entry paths have their own character, according to their functions and objectives. With these differences, this study identifies the relationship between student entry pathways, majors/types of previous high-level schools with GPA scores, and the length of the study period of students. Data mining in this study is to uses a priori algorithm. The Apriori algorithm is one of the classic data mining algorithms. The a priori algorithm is used to determine the most dominant factor in predicting student graduation rates. A priori algorithms are used so that computers can learn association rules, looking for patterns of relationships between one or more items in a dataset. The data in this study were taken from student data in SIAKAD, namely the student data of Raden Intan Lampung State Islamic University (UIN), Islamic Community Development Department, Class of 2015, the data used included the type of school of origin, entry route, GPA, and length of time. study period. From the results of the research, it is found that the rules or regulations that graduate students with a study period of 4 years / less and a GPA of 3.51 - 4.00 are students who enter through the Academic Interest (PMA) search path and from their school of high school (SMAN) with Value Support. 14,286 and 60% confidence value. These results can be used by universities in encouraging students from other entry paths and from other schools to graduate on time, such as students who entered through the PMA route and from high school from SMAN with certain efforts.

What’s Your STEMspiration?: Adaptation and Validation of A Survey Instrument

Millions of dollars each year are invested in intervention programs to broaden participation and improve bachelor degree graduation rates of students enrolled in science, technology, engineering, and mathematics (STEM) disciplines. The Virginia–North Carolina Louis Stokes Alliance for Minority Participation (VA-NC Alliance), a consortium of 11 higher education institutions and one federal laboratory funded by the National Science Foundation (NSF), is one such investment., The VA-NC Alliance partners implement evidence-based STEM intervention programs (SIPs) informed by research and specifically designed to increase student retention and graduation rates in STEM majors. The VA-NC Alliance is conducting an Alliance-wide longitudinal research project based in Social Cognitive Career Theory (SCCT) titled “What’s Your STEMspiration?” The goal of the research project is to assess the differentiated impacts and effectiveness of the Alliance’s broadening participation efforts and identify emergent patterns, adding to the field of knowledge about culturally responsive SIPs. In other words, “What’s Your STEMspiration?” explores what influences and inspires undergraduates to pursue a STEM degree and career; and how does the development of a STEM identity support students in achieving their goals. In order to complete this research, the research team developed a survey instrument to conduct the quantitative portion of the study. Two preliminary studies, statistical analysis, and cognitive interviews were used to develop and validate the survey instrument. This paper discusses the theoretical and conceptual frameworks and preliminary studies upon which the survey is built, the methodology used to validate the instrument, and the resulting final survey tool.

Can Undergraduate Research Participation Reduce the Equity Gap?

Undergraduate research (UGR), one of several high-impact practices (HIPs) in education, can positively impact student retention and graduation rates. However, not all students take advantage of UGR opportunities, with fewer students from underrepresented minority groups, those with first-generation status, and students eligible for a Pell grant or federally subsidized loan. We obtained retention and graduation data from our Office of Institutional Research and Planning for all UGR participants for academic years 2009–2010 to 2016–2017. We specifically focused on data for UGR participants from underrepresented demographics that historically have lower retention and graduation rates than those of the overall student body. We created Sankey-like ribbon diagrams to analyze the characteristics of UGR participants, whether they participated in UGR for 1 year or longer, their class standings when they started UGR, retention rates for 1st- and 2nd-year students for the year following their UGR participation, and graduation rates for all participants. Our data show that irrespective of demographics, students who participated in UGR were significantly more likely to persist in college and graduate within 6 years compared to students who did not. Persistence and success in college may depend on students’ socioeconomic status, sense of belonging, and other factors. Assessing the impact of a single HIP, such as UGR, on retention and graduation rates, can, therefore, be complicated. However, our study indicates that UGR participation can significantly improve persistence and success for students traditionally considered “at-risk,” irrespective of their socioeconomic status, family background, or class standing.. This information can be important for campus leaders and other stakeholders interested in facilitating student success and reducing the equity gap by incorporating UGR in more students’ college experiences. We describe our analytical methods and discusses our findings. We also demonstrate the effectiveness of Sankey-like diagrams for visualizing and analyzing large programmatic data sets, and as a tool for communicating program impacts to a general audience.

The Relationship between Faculty Diversity and Student Success in Public Community Colleges

ABSTRACT Community colleges serve the most diverse student populations in higher education yet have some of the lowest levels of faculty diversity in higher education. Retaining community college student cohorts through transfer/graduation is a goal, yet attaining this goal has been elusive, particularly for underrepresented minority (URM) community college students. Few studies have explored the impact of faculty diversity on the successful retention of URM community college students. This study used archival data for 120 public community colleges from the Integrated Postsecondary Education Data System (IPEDS) to calculate a Diversity Score for each college and ranked them by their overall level of faculty racial/ethnic variance to quantify the relationship between faculty diversity and student graduation, transfer, and drop-out rates. The findings suggest that there is a significant strong positive relationship between graduation, transfer, and drop-out rates for URM students of all race/ethnic categories when there are increases in faculty diversity. Exposure to a diverse faculty produces different outcomes in URM students.

Decomposing differences in Black student graduation rates between HBCU and non-HBCU Institutions: The devil is in the details

Six-year graduation rates of Black students at HBCUs are confirmed to match those of Black students at similar non-HBCUs. Digging deeper identifies which mechanisms that translate student and institutional characteristics into graduation rates still differ.

Prediction of student graduation accuracy using decision tree with application of genetic algorithms

Many of students who can’t complete the study promptly is a problem that needs to be faced with a fast and effective way. In the student’s education system is an important asset to the note the graduation rate of students promptly. Predicting graduation is very important for the institution to determine the strategic policies for the institution. The scope of the study is limited in performing accurate comparison between studies that only use Genetic Algorithm method and the research-based Genetic Algorithm using forward selection. Here we can conclude that the value of the highest accuracy is there in the Genetic Algorithm-based method Forward selection. Thus the Genetic Algorithm method with the selection of attribute-based Forward Selection is the best method for solving a problem in the prediction accuracy of graduation.

Predicting the Academic Success of Minority Male Students in a Public 4-Year Institution in the USA

Several studies have shown that nationally, retention and graduation rates of minority male students in higher education remains comparatively low. While most studies focus on factors accounting for low academic performance and achievement, and low retention and graduation rates of minority students, this study investigated the factors that contribute to minority male students’ success in a 4-year public institution. One hundred sixty successful minority male students took the College Student Experience Questionnaire (CSEQ). Using cumulative GPA (cGPA) as the criterion variable, three sets of explanatory variables (active learning index, cooperation among students, and college environment index) were regressed to determine the set of variables that best predict student success. The multiple linear regression result shows that the amount of time per week of studies toward academic work best predicts student success.

Repaying a Debt? The Performance of Morrill Act University Beneficiaries as Measured by Native Enrollment and Graduation Rates

Repaying a Debt?The Performance of Morrill Act University Beneficiaries as Measured by Native Enrollment and Graduation Rates Donna Feir (bio) and Maggie E. C. Jones (bio) the 1862 morrill act transferred "public" lands to several states and territories for the benefit of establishing colleges. The act is widely viewed as a watershed event in the development of the United States' postsecondary system (Goldin and Katz 2008; Key 1996). Recent quasi-experimental work by economists Isaac Ehrlich, Adam Cook, and Yong Yin (2018) suggests that the Morrill Act produced sizable educational and economic returns that were pivotal in the development of the U.S. economy. Absent from discussions of the Morrill Act are connections to Indigenous dispossession. The Land-Grab Universities (LGU) project (Lee and Ahtone 2020) directly connects the seizure and transfer of Indigenous land to the founding of a university system that has created economic returns to generations of Americans. While all universities benefit directly from the Indigenous lands on which their campuses are located, the university beneficiaries of the Morrill Act benefit in a very direct, traceable, and historically proximate fashion. This link makes the average economic marginalization and underrepresentation of Native students in the university system all the more problematic. Many notions of justice imply that universities whose endowments were seeded by Morrill Act lands have a greater obligation to current generations of Indigenous students whose ancestors were effectively deprived of their ability to provide opportunities for their children through the taking of their lands without fair compensation.1 We link the LGU database to the university-level data in the 2017–18 Integrated Post-secondary Education Data System (IPEDS) database to explore whether land-grant universities have fulfilled this obligation. Do the universities that received endowments from Morrill Act lands benefit American Indian and Alaska Native (AIAN) students today in a proportionate fashion to their returns on Indigenous lands? [End Page 129] The IPEDS Data and Linkage to the Land-Grab Universities Database IPEDS is the key dataset on postsecondary institutions from the National Center for Education Statistics (NCES). All universities are required to provide data, including enrollments and graduation rates, to the NCES, which then compiles information consistently across postsecondary institutions. We link the IPEDS data to the data created by Lee and Ahtone using the name of the university that benefited from Morrill Act lands. Specifically, we link the IPEDS data to the Universities.csv in the LGU database using the variable UNITID and university name. When universities have multiple campuses, we use the primary campus listed in the "city" variable in the LGU database. While our method is imperfect in attaching funds raised from the Morrill Act for university endowments to only one campus, the choice to use the primary campus is the most methodologically straightforward. We restrict attention to institutions covered by IPEDS Carnegie classifications 15, 16, 21, and 22, that is, research-intensive institutions that offer a wide range of baccalaureate programs and enroll graduate doctoral and master's degree students across a range of programs and disciplines. The chosen classifications cover all Morrill Act beneficiaries. This allows us to focus on universities that are similar to Morrill universities and ensures that any differences we observe between Morrill universities and other universities are not due to differences in university missions or sorts of degrees delivered. The specific metrics we use from the IPEDS data are (1) total, undergraduate, and graduate enrollment rates of AIAN students (i.e., the proportion of all students enrolled who identify as American Indian or Alaska Native); (2) the proportion of graduates who are AIAN who complete their program within 150 percent of normal time (150 percent graduation rate); (3) the 150 percent graduation rate of AIAN students; and (4) the difference between the 150 percent graduation rate of white students and that of AIAN students. Do Morrill Act Beneficiaries Enroll and Graduate a Greater Percentage of Indigenous Students as a Proportion of Their Student Base? Indigenous students are generally underrepresented in the university system (Postsecondary National Policy Institute 2019). At all universities, only around 0.3 percent of fall enrollments in 2017–18 were identified as AIAN, while the AIAN population accounted for close to...

Helping Students FIG-ure It Out: A Large-Scale Study of Freshmen Interest Groups and Student Success

Freshman seminars are a ubiquitous offering in higher education, but they have not been evaluated using matched comparisons with data at scale. In this work, we use transcript data on over 76,000 students to examine the impact of first-year interest groups (FIGs) on student graduation and retention. We first apply propensity score matching on course-level data to account for selection bias. We find that graduation and re-enrollment rates for FIG students were higher than non-FIG students, an effect that was more pronounced for self-identified underrepresented racial minority students. We then employ topic modeling to analyze survey responses from over 12,500 FIG students to find that social aspects of FIGs were most beneficial to students. Interestingly, references to social aspects were not disproportionately present in the responses of self-identified underrepresented racial minority students.