scholarly journals Predicting key educational outcomes in academic trajectories: a machine-learning approach

2020 ◽  
Vol 80 (5) ◽  
pp. 875-894 ◽  
Author(s):  
Mariel F. Musso ◽  
Carlos Felipe Rodríguez Hernández ◽  
Eduardo C. Cascallar
Keyword(s):  
Machine Learning ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Degree Completion ◽  
Educational Outcomes ◽  
Background Information ◽  
Grade Point ◽  
Methodological Approaches ◽  
Artificial Neural ◽  
Academic Retention

Abstract Predicting and understanding different key outcomes in a student’s academic trajectory such as grade point average, academic retention, and degree completion would allow targeted intervention programs in higher education. Most of the predictive models developed for those key outcomes have been based on traditional methodological approaches. However, these models assume linear relationships between variables and do not always yield accurate predictive classifications. On the other hand, the use of machine-learning approaches such as artificial neural networks has been very effective in the classification of various educational outcomes, overcoming the limitations of traditional methodological approaches. In this study, multilayer perceptron artificial neural network models, with a backpropagation algorithm, were developed to classify levels of grade point average, academic retention, and degree completion outcomes in a sample of 655 students from a private university. Findings showed a high level of accuracy for all the classifications. Among the predictors, learning strategies had the greatest contribution for the prediction of grade point average. Coping strategies were the best predictors for degree completion, and background information had the largest predictive weight for the identification of students who will drop out or not from the university programs.

scholarly journals Supervised Learning Applied to Graduation Forecast of Industrial Engineering Students

2022 ◽  
Vol 11 (1) ◽  
pp. 325-337
Author(s):  
Natalia Gil ◽  
Marcelo Albuquerque ◽  
Gabriela de
Keyword(s):  
Machine Learning ◽  
High School ◽  
Logistic Regression ◽  
Supervised Learning ◽  
Grade Point Average ◽  
Engineering Students ◽  
Learning Algorithm ◽  
Industrial Engineering ◽  
Machine Learning Algorithm ◽  
Grade Point

<p style="text-align: justify;">The article aims to develop a machine-learning algorithm that can predict student’s graduation in the Industrial Engineering course at the Federal University of Amazonas based on their performance data. The methodology makes use of an information package of 364 students with an admission period between 2007 and 2019, considering characteristics that can affect directly or indirectly in the graduation of each one, being: type of high school, number of semesters taken, grade-point average, lockouts, dropouts and course terminations. The data treatment considered the manual removal of several characteristics that did not add value to the output of the algorithm, resulting in a package composed of 2184 instances. Thus, the logistic regression, MLP and XGBoost models developed and compared could predict a binary output of graduation or non-graduation to each student using 30% of the dataset to test and 70% to train, so that was possible to identify a relationship between the six attributes explored and achieve, with the best model, 94.15% of accuracy on its predictions.</p>

scholarly journals Modeling Wording Effects Does Not Help in Recovering Uncontaminated Person Scores: A Systematic Evaluation With Random Intercept Item Factor Analysis

2021 ◽  
Vol 12 ◽  
Author(s):  
María Dolores Nieto ◽  
Luis Eduardo Garrido ◽  
Agustín Martínez-Molina ◽  
Francisco José Abad
Keyword(s):  
Factor Analysis ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Model Fit ◽  
Systematic Evaluation ◽  
Grade Point ◽  
Independent Variables ◽  
Random Intercept ◽  
Item Factor Analysis ◽  
The Relationship

The item wording (or keying) effect consists of logically inconsistent answers to positively and negatively worded items that tap into similar (but polarly opposite) content. Previous research has shown that this effect can be successfully modeled through the random intercept item factor analysis (RIIFA) model, as evidenced by the improvements in the model fit in comparison to models that only contain substantive factors. However, little is known regarding the capability of this model in recovering the uncontaminated person scores. To address this issue, the study analyzes the performance of the RIIFA approach across three types of wording effects proposed in the literature: carelessness, item verification difficulty, and acquiescence. In the context of unidimensional substantive models, four independent variables were manipulated, using Monte Carlo methods: type of wording effect, amount of wording effect, sample size, and test length. The results corroborated previous findings by showing that the RIIFA models were consistently able to account for the variance in the data, attaining an excellent fit regardless of the amount of bias. Conversely, the models without the RIIFA factor produced increasingly a poorer fit with greater amounts of wording effects. Surprisingly, however, the RIIFA models were not able to better estimate the uncontaminated person scores for any type of wording effect in comparison to the substantive unidimensional models. The simulation results were then corroborated with an empirical dataset, examining the relationship between learning strategies and personality with grade point average in undergraduate studies. The apparently paradoxical findings regarding the model fit and the recovery of the person scores are explained, considering the properties of the factor models examined.

scholarly journals Examining Some of Students’ Views on the Nature of Science (NOS) in Traditional Lecture Format Teaching Environment

2021 ◽  
Vol 5 (2) ◽  
pp. 69-77
Author(s):  
Issa I. Salame ◽  
Shirley Dong
Keyword(s):  
Grade Point Average ◽  
Science Teaching ◽  
Nature Of Science ◽  
Teaching And Learning ◽  
Science Research ◽  
Learning Activities ◽  
Background Information ◽  
Algorithmic Problem ◽  
Grade Point ◽  
Science Courses

The preparation of a scientifically literate society is the main goal of science education throughout the world and this has resulted in the emphasis of nature of science in the curriculum. The purpose of this research project is to examine the aforementioned students’ views on NOS tenets, its relationship to their academic achievements and background, and how it changes through their study of science. The study took place at the City College of New York, an urban, commuter, public college, and minority serving institute. The research data was collected through the administration of a survey that contained three of the NOS questions and academic and background information about the students. The data suggest that students possess inadequate understanding of the nature of science when they begin their academic fields of science study. This inadequate understanding is resistant to change in traditional science teaching settings. The data provide evidence that the inadequate understanding of nature of science does not change as the result of exposure to science courses, the field of science studied, and the students’ academic achievement as measured by grade point average. Our data show that traditional instruction in college science courses does not address nature of science and does not cause a conceptual change in the students’ understanding of NOS. The lack of correlation between students’ understanding of nature of science and credits completed or grade point average could be attributed to students relying on rote-learning and algorithmic problem-solving to achieve high grades and succeed in science, which hinders their meaningful learning of science and the development of conceptual understanding. Thus, science teaching and instruction should address naïve conception on the NOS and changes the instruction methods to consider NOS naïve conceptions and learning challenges. Science teaching and learning curriculum and instruction should immerse students in science learning activities that nurtures their understanding of the nature of science through participating in novel science research and inquiry-based learning activities.

scholarly journals Diferencias individuales en aprendizaje autorregulado de estudiantes de los Grados de Educación: género, especialidad, notas y desempeño académico

2020 ◽  
Vol 38 (2) ◽  
pp. 453-473
Author(s):  
Nerea Larruzea-Urkixo ◽  
Maria Olga Cardeñoso Ramírez
Keyword(s):  
Academic Performance ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Self Regulation ◽  
Female Students ◽  
Male Students ◽  
Grade Point ◽  
Self Regulated Learning ◽  
Regulatory Processes ◽  
Regulated Learning

Introducción: conocer las diferencias en los procesos de autorregulación del aprendizaje del alumnado actual es clave para la mejora de la formación en nuestras universidades. El objetivo de este estudio es analizar la variabilidad en dichos procesos en función del género, la especialidad, las notas (de acceso y de grado) y otras variables de desempeño académico. Método: participaron en el estudio 456 estudiantes (335 mujeres y 119 hombres) de los Grados en Educación Infantil y Primaria que completaron la versión en español del Motivated Strategies for Learning Questionnaire (Ramírez, Canto, Bueno & Echezarreta, 2013) junto a datos relativos al desempeño académico. Resultados: Se mostró la existencia de diferencias en aprendizaje autorregulado en función del género, pero no de la especialidad ni de la interacción entre género*especialidad. También se reveló que las alumnas poseían mayor autorregulación que los alumnos tanto en variables motivacionales como en estrategias de aprendizaje. A continuación, se hallaron diferencias en aprendizaje autorregulado en función de la nota de acceso, de grado y de la interacción género*nota de grado. Aunque de manera general estos datos confirman que “a mayor nota de acceso, mejor autorregulación”, los resultados desvelaron un declive del alumnado con mejores notas de grado en varias subescalas exceptuando en aprendizaje entre iguales. Finalmente, se mostró que las alumnas perciben la carrera con mayor dificultad, dedican más horas y presentan un mejor rendimiento académico de lo esperado. Discusión: Estas diferencias entre el alumnado deberían ser consideradas para potenciar la autorregulación en las aulas. Introduction: Identifying differences in self-regulatory processes among current students is key to improve training in our universities. The aim of this study is to analyze the variability in the aforementioned processes according to gender, teaching specialty, grades (admission grade and grade point average, GPA) and other variables related to academic performance. Method: 456 Primary Education and Early Childhood Education students participated in the study (335 women and 119 men) by completing the Spanish version of the Motivated Strategies for Learning Questionnaire (Ramírez, Canto, Bueno & Echezarreta, 2013). Results: Differences were found in self-regulated learning based on gender, but not on specialty or on the interaction between gender*specialty. It was also shown that female students had greater self-regulatory skills than male students in both motivational variables and learning strategies. Besides, differences were found in self-regulated learning according to admission grade, grade point average and the interaction gender*grade point average. Although, overall, the data obtained confirm that "the higher the admission grade, the better self-regulatory skills", results revealed a decline among students with better grades in several subscales except for peer learning. Finally, it was shown that female students have a higher awareness of the degree’s difficulty, dedicate more hours and present a better academic performance than expected. Discussion: These differences between students should be considered in order to promote self-regulation in the classroom.

scholarly journals Admission Criteria for MBA Programs

SAGE Open ◽  
2016 ◽  
Vol 6 (4) ◽  
pp. 215824401666939 ◽  
Author(s):  
Silvana Dakduk ◽  
José Malavé ◽  
Carmen Cecilia Torres ◽  
Hugo Montesinos ◽  
Laura Michelena
Keyword(s):  
Grade Point Average ◽  
Student Performance ◽  
Learning Strategies ◽  
Work Experience ◽  
Admission Criteria ◽  
Mba Programs ◽  
Grade Point ◽  
Personal Traits ◽  
Achievement Expectations ◽  
Graduate Management Admission Test

This paper reports a review of studies on admission criteria for MBA programs. The method consisted in a literary review based on a systematic search in international databases (Emerald, ABI/INFORM Global, ProQuest Education Journals, ProQuest European Business, ProQuest Science Journal, ProQuest Research Library, ProQuest Psychology Journals, ProQuest Social Science Journals and Business Source Complete) of studies published from January 1990 to December 2013, which explore the academic performance of students or graduates of MBA programs. A quantitative review was performed. Results show that most researchers studied relations between GMAT (Graduate Management Admission Test) and UGPA (Undergraduate Grade Point Average) as predictors of GGPA (Graduate Grade Point Average). On the other hand, work experience and personal traits (such as personality, motivation, learning strategies, self-efficacy beliefs and achievement expectations) and their relation with GGPA had been less studied, and results are not consistent enough to consider them valid predictors of student performance at this time.

SELF-REGULATED LEARNING AND ACADEMIC ACHIEVEMENT AMONG MEDICAL STUDENTS: AN ACCELERATED PROSPECTIVE COHORT STUDY

2019 ◽  
pp. 22-29
Author(s):  
Van Hung Nguyen ◽  
Laohasiriwong Wongsa
Keyword(s):  
Academic Achievement ◽  
Medical Students ◽  
Goal Orientation ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Use Of Self ◽  
Grade Point ◽  
Self Regulated Learning ◽  
Regulated Learning ◽  
Academic Year

Objectives: To determine the relationships between the use of self-regulated learning strategies and academic achievement among Vietnamese medical students. Methods: An accelerated prospective cohort study among 623 students at a public medical university, Vietnam was conducted during the academic year 2012-2013. Fourteen self-regulated learning subscales including intrinsic/extrinsic goal orientation, task values, self-efficacy for learning, control of learning beliefs, rehearsal, elaboration, organization, critical thinking, meta-cognitive strategies, time and study environment, effort regulation, peer learning, and help seeking were measured using the Motivated Strategies for Learning Questionnaire. The Grade Point Average was recorded through two consecutive semesters of the academic year 2012-2013. Data were collected at two points in time (once each semester). Generalized Estimating Equation was applied to explore any relationships between the use of self-regulated learning subscales and Grade Point Average, adjusting for the effects of within cluster correlation, National Medical Admission Test scores, and times of measurement, depression, anxiety, stress, and demographic covariates. Results: Results from multivariate analysis revealed that extrinsic goal orientation, time and study environment, and effort regulation were found to be significantly positively associated with Grade Point Average (mean difference: 0.932; 95%CI: 0.344 to 1.528). Conclusions: The use of self-regulated learning strategies can be helpful for improving of academic achievement among Vietnamese medical students. Key words: self-regulated learning, academic achievement, medical students, Vietnam

scholarly journals Modeling wording effects does not help in recovering uncontaminated person scores: A systematic evaluation with random intercept item factor analysis

2021 ◽  
Author(s):  
María Dolores ◽  
Luis Eduardo Garrido ◽  
Francisco José Abad ◽  
Agustín Martínez-Molina
Keyword(s):  
Factor Analysis ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Model Fit ◽  
Systematic Evaluation ◽  
Grade Point ◽  
Independent Variables ◽  
Random Intercept ◽  
Item Factor Analysis ◽  
The Relationship

The item wording (or keying) effect consists of logically inconsistent answers to positively and negatively worded items that tap into similar (but polarly opposite) content. Previous research has shown that this effect can be successfully modeled through the random intercept item factor analysis (RIIFA) model, as evidenced by the improvements in model fit in comparison to models that only contain substantive factors. However, little is known regarding the capability of this model in recovering the uncontaminated person scores. To address this issue, the current study analyzed the performance of the RIIFA approach across three types of wording effects proposed in the literature: carelessness, item verification difficulty, and acquiescence. In the context of unidimensional substantive models, four independent variables were manipulated using Monte Carlo methods: type of wording effect, amount of wording effect, sample size, and test length. The results corroborated previous findings by showing that the RIIFA models were consistently able to account for the variance in the data, attaining excellent fit regardless of the amount of bias. Conversely, the models without the RIIFA factor produced increasingly poorer fit with greater amounts of wording effects. Surprisingly, however, the RIIFA models were not able to better estimate the uncontaminated person scores for any type of wording effect in comparison to the substantive unidimensional models. The simulation results were then corroborated with an empirical dataset examining the relationship between learning strategies and personality with grade point average in undergraduate studies. The apparently paradoxical findings regarding model fit and the recovery of the person scores are explained in light of the properties of the factor models examined.

scholarly journals An Overview of Convolutional Neural Network: Its Architecture and Applications

2018 ◽  
Author(s):  
Shadman Sakib ◽  
Nazib Ahmed ◽  
Ahmed Jawad Kabir ◽  
Hridon Ahmed
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Learning Strategies ◽  
Learning Tasks ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Many

With the increase of the Artificial Neural Network (ANN), machine learning has taken a forceful twist in recent times. One of the most spectacular kinds of ANN design is the Convolutional Neural Network (CNN). The Convolutional Neural Network (CNN) is a technology that mixes artificial neural networks and up to date deep learning strategies. In deep learning, Convolutional Neural Network is at the center of spectacular advances. This artificial neural network has been applied to several image recognition tasks for decades and attracted the eye of the researchers of the many countries in recent years as the CNN has shown promising performances in several computer vision and machine learning tasks. This paper describes the underlying architecture and various applications of Convolutional Neural Network.

Mobile CGPA Monitoring System

2018 ◽  
pp. 10-21
Author(s):  
Muhammad Aminu Umar ◽  
Abdullahi Shuru ◽  
Aliyu Muhammad Kufena ◽  
Mohammed Yahaya Tanko ◽  
Ahmed Aminu Sambo ◽  
...  
Keyword(s):  
Academic Performance ◽  
Grade Point Average ◽  
Learning Strategies ◽  
Performance Monitoring ◽  
Self Directed Learning ◽  
Grade Point ◽  
Cumulative Grade Point Average ◽  
Academic Standing ◽  
Course Work ◽  
Directed Learning

The digital age also referred to as information age is characterized with the ability to transfer information freely and quickly. This makes self-directed learning strategies to gain ground. Self-directed learning facilitate students or learners to take ownership of their learning. Individual academic performance monitoring is an essential part of self-directed learning. In order to achieve this, certain performance measuring technique is required to guide learners in monitoring their performance such as Cumulative Grade point average (CGPA). Students' Academic performance of is characterized by the overall performance in both test, course work and examinations each year which culminates in a grade point average. This has help in determining the academic standing of students. Therefore, this chapter proposed a mobile CGPA calculator to help students monitor and measure their performance during the learning process. The system is proven to be effective against the required functionalities.

Sign in / Sign up

Export Citation Format

Share Document