Past Academic Performance Research Articles

A Machine Learning Approach to Optimal Group Formation Based on Previous Academic Performance

In today’s educational institutions, student performance can vary widely due to differences in cognition, motivation, and environmental factors. These variations create challenges in achieving optimal learning outcomes. To address these challenges, Optimal Group Formation (OGF) has emerged as a promising research area. Optimal Group Formation (OGF) aims to form student groups that maximize learning efficiency based on past academic performance. Group formation problems are inherently complex and time-consuming, but their applications are extensive, spanning from manufacturing systems to educational contexts. This paper introduces a machine learning-based model designed to create optimal student groups using academic records as the primary input. The goal is to enhance overall group performance and reduce error rates by organizing students into cohesive, efficient teams. What sets this research apart is its focus on educational group formation, leveraging machine learning to improve collaborative learning outcomes. The paper also reviews prior research, emphasizing the importance of Optimal Group Formation (OGF) in various fields and its relevance in education. The model’s effectiveness is demonstrated through comparative analysis, showcasing its potential to improve group dynamics in both theoretical and lab-based courses. Ultimately, the aim is to improve educational outcomes by ensuring that student groups are optimally balanced and structured.

Machine Learning-Based Academic Result Prediction System

Students' academic performance is a critical issue as it decides his/her career. It is pivotal for the educational institutes to track the performance record because it can help to enhance the standard of their quality education. Thus, the role of the academic result prediction system comes into existence which uses semester grade point average (SGPA) as a metric. The proposed work aims to create a model that can forecast the SGPA of students based on certain traits. It predicts the result in the form of SGPA of computer science students considering their past academic performance, study, and personal habits during their academic semester using different machine learning models, and to compare them based on different accuracy parameters. Some models that are widely used and are found effective in this field are regression algorithms, classification algorithms, and deep learning techniques. The results conclude that deep learning techniques are the most effective in the proposed work because of their high accuracy and performance, depending upon the attributes used in the prediction.

Predicting students' performance in English and Mathematics using data mining techniques.

This study attempts to predict secondary school students’ performance in English and Mathematics subjects using data mining (DM) techniques. It aims to provide insights into predictors of students’ performance in English and Mathematics, characteristics of students with different levels of performance, the most effective DM technique for students’ performance prediction, and the relationship between these two subjects. The study employed the archival data of students who were 16 years old in 2019 and sat for the Malaysian Certificate of Examination (MCE) in 2021. The learning of English and Mathematics is a concern in many countries. Three main factors, namely students’ past academic performance, demographics, and psychological attributes were scrutinized to identify their impact on the prediction. This study utilized the Orange software for the DM process. It employed Decision Tree (DT) rules to determine the characteristics of students with low, moderate, and high performance in English and Mathematics subjects. DT and Naïve Bayes (NB) techniques show the best predictive performance for English and Mathematics subjects, respectively. Such characteristics and predictions may cue appropriate interventions to improve students’ performance in these subjects. This study revealed students’ past academic performance as the most critical predictor, as well as a few demographics and psychological attributes. By examining top predictors derived using four different classifier types, this study found that students’ past Mathematics performance predicts their MCE English performance and students’ past English performance predicts their MCE Mathematics performance. This finding shows students’ performances in both subjects are interrelated.

Helping some and harming others: Homework frequency and tradeoffs in student performance

The authors of this article examine the potential for increased student learning and retention through more frequent assignments. They conduct a field experiment that investigates whether student knowledge retention can be improved by increasing the frequency of homework assignments, motivating students to have more exposure to the material, and reducing the incentives for students to procrastinate. They find that the impact of the treatment on student performance varies based on the student’s past academic performance. Students on the lower end of the academic performance distribution benefit from the structure imposed by more frequent assignments and perform better. However, students with high prior academic performance are harmed by the intervention. The final exam scores of high-performing students are lower in courses with higher assignment frequency.

THE EFFECT OF ONLINE EDUCATION ON THE ACADEMIC PERFORMANCE OF STUDENTS DURING COVID-19 PANDEMIC: EVIDENCE FROM KAZAKHSTAN

Purpose of the research. This study explores COVID19-imposed online education at one of the universities in Kazakhstan to understand whether and in what way it has affected students’ academic performance.Methodology. We use several methodologies, such as the principal component analysis, the nearestneighbour propensity score matching and the latent variable multilevel model.Originality / value of the research. To the best of our knowledge, this is the first attempt to estimate the effect of COVID19-imposed online teaching on academic performance in Kazakhstan.Findings. Though our data suggest that the students exposed to online education had slightly lower academic performance than the earlier cohort of similar students who studied in class, this result is not statistically significant. In fact, for both cohorts of students, their past academic performance reflecting their academic abilities and attitudes, such as university entry test score and past accumulative GPA, matter much more than the mode of study. However, we found out that certain technical variables which characterise the “quality” of Zoom® sessions affect students’ academic performance. Specifically, using a smartphone instead of a personal computer to enter a class conducted in Zoom® negatively affects students’ achievement. Some other characteristics also produce expected effects though they turned out to be statistically insignificant possibly due to aggregation and a small dataset.

Choice of Management Specialisation Courses: Assessing the Role of Consideration of Prospects, and Individual and Social Factors

This paper presents the results of a survey that examined the decision-making variables influencing the specialisation choice of undergraduate management students from a consumer behaviour perspective. Tribhuvan University has designed their undergraduate BBA programme by offering students the facility to customise their educational programme through the specialisation in four different areas: banking & finance, industry and services management, micro enterprise management, and sales and marketing management. Using the factorial ANCOVA research design and multistage sampling technique, 114 students from 10 out of 25 campuses, the study concludes that the past academic performance (individual factor) has the significant effect on selecting the specialisation courses among banking and finance, and marketing management. The effect of social factor and future prospect consideration have insignificant effect on SC after controlling the covariate individual factor (past academic performance). However, the significant interaction of SF_I and FPC_I in the full factorial model implies that there is at least effect of the intensities of SF and FPC on the specialisation course selection among the TU BBA students.

Emotional and Cognitive Aptitudes and Successful Academic Performance: Using the ECCT

Understanding factors that influence academic performances is vital. The aim of this study is to longitudinally test, with three timepoints, the unique contribution of several predictors to academic performance. In a sample of 796 Ecuadorian students, dominance analyses were performed with the R program to test the relative and unique importance of the seven variables under study (verbal aptitude, numerical aptitude, abstract reasoning, emotional regulation scenarios, emotional regulation self-questionnaire, and academic performance measured in timepoint one and two) for academic performance, measured in timepoint three in the entire sample and separately in each of the ten degrees in the academic center. Results show that the strongest predictors are past academic performance, followed by gender, numerical aptitude, scenarios, verbal aptitude, abstract reasoning, and, finally, the emotional regulation self-questionnaire. This study contributes to explaining the complex topic of academic performance. More studies are needed in order to better understand the role played by emotional intelligence, as well as differences between different degrees or areas of study.

How does Academic Performance Increase Virtual Popularity? A Case of Facebook Usage among Indian College Students

The debate on the positive and negative impact of Facebook on youth particularly on their academic performance has become prevalent in academic discourses. The previous studies show mixed findings of the effect of Facebook on academic performance as well as on other education-related variables. Though the role of Facebook in academics is well explored, however, the impact of academics on Facebook usage has not been examined. The present study examines the reverse possibility i.e. effect of study and academic performance on Facebook usage. Two offline survey studies were conducted on Indian college students. Study one was conducted on 250 undergraduate students (mean age = 20.15; 101 female participants) which shows a significant positive impact of past academic performance on Facebook friendship. Study two was conducted on 317 undergraduate students (mean age = 19.95; 259 females) with two additional indicators of Facebook usage i.e. time spent on Facebook and attitude toward Facebook use. Results of study two also show a positive impact of academic performance on Facebook friendship, however, no such impact is found for other indicators of Facebook use. Overall research shows academic achievement positively influences the virtual popularity of individuals, especially for college students.

Assessment of Diversity Outcomes in American Medical School Admissions: Applying the Grutter Legitimacy Principles

In the last 30 years, except for female participation, the enrollment of Latinx, African Americans, Native Americans, Alaskan natives, and disadvantaged students in medical school has been constant; however, increasing enrollment of these minority populations is feasible, if admissions committees make two changes in approach. First, the traditional belief that matriculation merit is a linear function of past academic performance must be rejected. Second, once the threshold needed to complete medical school in four years and to pass licensing examinations at the first attempt has been met, all candidates are equally qualified, and matriculation decisions must be based, in part, on societal interests. In Grutter vs. Bollinger, the United States Supreme Court determined that graduate admission committees can and should consider societal interests. Each admission decision represents a substantial government investment in each student, as the Medicare Act directly subsidizes much of the cost of medical education. As Grutter explained, there is a societal interest in the public having confidence in, and access to, the medical school training that will prepare tomorrow’s medical, professional, and political leaders. Our analysis suggests that medical school admissions are biased towards academic achievement in matriculants, beyond acceptable thresholds for graduation and licensure. We believe medical schools must shift their admissions strategies and consider noncognitive factors in all candidates as determinative once minimum acceptable academic standards have been met.

Correlates of Poor Sleep and Subsequent Risk of Misdiagnosis in College Students Presenting with Cognitive Complaints.

To examine the relationships of poor sleep to both subjective and objective cognitive functioning, attention deficit hyperactivity disorder (ADHD) and sluggish cognitive tempo (SCT) symptoms, and mental health variables in college students, controlling for noncredible symptom reporting and noncredible performance. 99 undergraduate students (Mage=19.9, SD=1.1), 60% female and 72% first-year students, completed a neuropsychological battery and self-report questionnaires at a single lab visit. 56% of the sample identified as "poor sleepers" (>5 on the Pittsburgh Sleep Quality Index [PSQI]). Poor sleepers reported worse current (college grade point average [GPA]) but not past (high school GPA, American college test [ACT] score) academic performance. Additionally, they reported more mental health concerns, including depression and stress, but not anxiety. Poor sleepers reported more functional impairment and subjective cognitive concerns, including more Diagnostic and Statistical Manual of Mental Disorders (DSM) inattentive and hyperactive/impulsive symptoms, more SCT symptoms, and more executive dysfunction, even when controlling for depressive symptoms. However, poor sleepers did not differ from good sleepers on measures of objective cognition. ADHD and SCT symptoms and concerns in college students may be related to poor sleep, which can lead to misdiagnosis for individuals presenting with ADHD-like complaints for the first time in college. Sleep difficulties may be modifiable with empirically supported sleep interventions; thus, in assessment for either of these presentations, a careful sleep history should be taken.

Differential effects of individual and school factors on the academic trajectories of Japanese dental students.

Dental students follow different academic performance trajectories in response to increasing study load, based on individual and school factors. Group-based trajectory modeling is useful for clarifying the underlying trajectory patterns of students' academic performance and its determinants. To our knowledge, no studies have used group-based trajectory modeling to examine the effects of individual and school factors on academic performance trajectories in dental students. The objective of this study was to examine the effects of individual and school factors on academic performance trajectories in Japanese dental students using group-based trajectory modeling. The analytical sample consists of 103 dental students admitted to Tokyo Medical and Dental University, Tokyo, Japan, in 2013 and 2014. Students' academic performance was assessed by biannual grade point average (GPA) score and GPA in the preclinical phase (second to fourth grade) was used for this study. We used group-based trajectory modeling to categorize students' GPA trajectories into different groups. A multinomial logistic regression model was fit to examine associations between students' individual and school factors, and odds of being assigned to certain GPA groups. GPA trajectories of dental students were classified into 4 different groups. Students' past academic performance in high school was associated with lower GPA trajectories and withdrawal or repeating years. Males were significantly associated with lower GPA trajectories and withdrawal or repeating years, even after adjusting for past academic performance. Past lower academic performance and being male were positively associated with lower academic performance trajectories in Japanese dental students.

The Importance of Being Honest: Correlating Self-Report Accuracy and Network Centrality with Academic Performance

ABSTRACTThis study investigates the correlation of self-report accuracy with academic performance. The sample was composed of 289 undergraduate students (96 senior and 193 junior) enrolled in two engineering classes. Age ranged between 22 and 24 years, with a slight over representation of male students (53%). Academic performance was calculated based on students' final grades in each class. The tendency to report inaccurate information was measured at the end of the Raven Progressive Matrices Test, by asking students to report their exact finishing times. We controlled for gender, age, personality traits, intelligence, and past academic performance. We also included measures of centrality in their friendship, advice and trust networks. Correlation and multiple regression analyses results indicate that lower achieving students were significantly less accurate in self-reporting data. We also found that being more central in the advice network was correlated with higher performance (r = .20, p < .001). The results are aligned with existing literature emphasizing the individual and relational factors associated with academic performance and, pending future studies, may be utilized to include a new metric of self-report accuracy that is not dependent on academic records.

Predicting patterns of change and stability in student performance across a medical degree.

Evidence of predictive validity is essential for making robust selection decisions in high-stakes contexts such as medical student selection. Currently available evidence is limited to the prediction of academic performance at single points in time with little understanding of the factors that might undermine the predictive validity of tests of academic and non-academic qualities considered important for success. This study addressed these issues by predicting students' changing performance across a medical degree and assessing whether factors outside an institution's control (such as the uptake of commercial coaching) impact validity. Three cohorts of students (n = 301) enrolled in an undergraduate medical degree from 2007-2013 were used to identify trajectories of student academic performance using growth mixture modelling. Multinomial logistic regression assessed whether past academic performance, a test of cognitive ability and a multiple mini-interview could predict a student's likely trajectory and whether this predictive validity was different for those who undertook commercial coaching compared with those who didn't. Among the medical students who successfully graduated (n = 268), four unique trajectories of academic performance were identified. In three trajectories, performance changed at the time when learning became more self-directed and focused on clinical specialties. Scores on all selection tests, with the exception of a test of abstract reasoning, significantly affected the odds of following a trajectory that was consistently below average. However, selection tests could not distinguish those whose performance improved across time from those whose performance declined after an average start. Commercial coaching increased the odds of being among the below-average performers, but did not alter the predictive validity of the selection tests. Identifying distinct groups of students has important implications for selection, but also for educating medical students. Commercial coaching may result in selecting students who are less suited for coping with the rigours of medical studies.

Shadow Education in Malaysia: Identifying the Determinants of Spending and Amount of Time Attending Private Supplementary Tutoring of Upper Secondary School Students

This paper examines the determinants of spending and the amount of time attending private supplementary tutoring, or commonly known as private tuition, in Malaysia. Based on 343 self-reported questionnaires with upper secondary students across three states in Malaysia and using multiple regression analysis, we identified ethnicity, father’s level of education and past academic performance as significant determinants of spending and amount of time attending private tuition. However, interestingly, we found that while geographical location and participation in internal tuition in schools were also determinants of spending, these two were not significant in determining the amount of time attending private supplementary tutoring. The identification of determinants of spending and amount of time, and in addition, the differences between these two illustrates the economic and educational dimensions of shadow education. More importantly, the insight also contributes to the formulation of possible interventions that can improve quality and reduce inequality in the mainstream education system.

Teaching psychology in Australia: Does class attendance matter for performance?

ObjectiveThe value of course attendance is well documented, and has been linked to improved performance in the past. The current study aimed to add to this body of knowledge by examining a robust sample of students (six cohorts across two content domains) within the context of psychology undergraduate courses and specifically within Australian universities. To date, little data is available focusing on the issue of class attendance for psychology students in Australia.MethodData were collected from students during classes using paper and pencil questionnaires in which previous grades and attendance were recorded along with student number. Student number was subsequently matched to observed final grades which were recorded, before the student number was deleted to provide a de‐identified data set.ResultsUsing hierarchical linear modelling we found that course attendance was positively related to objective performance, providing additional findings to bolster evidence for the relationship between course attendance and objective performance while controlling for self‐reported past academic performance. Furthermore, we did not find any significant variance in this relationship across course content, attesting to the robust nature of the link between class attendance and performance.ConclusionOur data pre‐date the major innovations in online teaching of the last few years, but the findings provide an important baseline and arguably have practical implications for the teaching of psychology within Australian universities.

Using creativity to predict future academic performance: An application of Aurora's five subtests for creativity

In this study, we investigated the specific contribution of creativity, as assessed by the five creativity subtests of the Aurora Battery, to future academic performance, independently of past academic performance. Specifically, in a sample of 1165 7th grade students (UK Year 8, 48.3% female) we first looked at whether the factorial structure of the five subtests was better explained by a domain-general (i.e., the g-factor of creativity) or domain-specific (i.e., verbal, numerical, figural) model of creativity. Then, in a subsample of 315 students (46.3% females) we estimated a structural equation model to explore the mediating role of creativity between students' performance on different academic tests, specifically the Key Stage 2 test (KS2), taken almost two years before Aurora, and the General Certificate of Secondary Education exams (GCSE), taken almost three and a half years after Aurora. Results showed that Aurora's subtest scores were better represented by a single latent factor (a general creativity factor) than multiple (domain-specific) creativity factors. Furthermore, this creativity factor predicted individuals' performance on the GCSE four years after taking Aurora, even after controlling for previous academic performance. In addition, creativity mediated the relationship between the KS2 and GCSE. These results suggest that a domain-general form of creativity contributes to future academic performance above and beyond other academics skills.

Student-directed retrieval practice is a predictor of medical licensing examination performance.

IntroductionA large body of evidence indicates that retrieval practice (test-enhanced learning) and spaced repetition increase long-term information retention. Implementation of these strategies in medical curricula is unfortunately limited. However, students may choose to apply them autonomously when preparing for high-stakes, cumulative assessments, such as the United States Medical Licensing Examination Step 1. We examined the prevalence of specific self-directed methods of testing, with or without spaced repetition, among preclinical students and assessed the relationship between these methods and licensing examination performance.MethodsSeventy-two medical students at one institution completed a survey concerning their use of user-generated (Anki) or commercially-available (Firecracker) flashcards intended for spaced repetition and of boards-style multiple-choice questions (MCQs). Other information collected included Step 1 score, past academic performance (Medical College Admission Test [MCAT] score, preclinical grades), and psychological factors that may have affected exam preparation or performance (feelings of depression, burnout, and test anxiety).ResultsAll students reported using practice MCQs (mean 3870, SD 1472). Anki and Firecracker users comprised 31 and 49 % of respondents, respectively. In a multivariate regression model, significant independent predictors of Step 1 score included MCQs completed (unstandardized beta coefficient [B] = 2.2 × 10− 3, p < 0.001), unique Anki flashcards seen (B = 5.9 × 10− 4, p = 0.024), second-year honours (B = 1.198, p = 0.002), and MCAT score (B = 1.078, p = 0.003). Test anxiety was a significant negative predictor (B= − 1.986, p < 0.001). Unique Firecracker flashcards seen did not predict Step 1 score. Each additional 445 boards-style practice questions or 1700 unique Anki flashcards was associated with an additional point on Step 1 when controlling for other academic and psychological factors.ConclusionsMedical students engage extensively in self-initiated retrieval practice, often with spaced repetition. These practices are associated with superior performance on a medical licensing examination and should be considered for formal support by educators.

The Relationship Between Self-Efficacy and Academic Achievement: A 5-Year Panel Analysis

The purpose of this study was to examine the longitudinal causal relationship among Korean students’ past academic performance, self-efficacy beliefs, and academic achievement. The study used an autoregressive cross-lagged model to assess the casual ordering of self-efficacy beliefs and academic achievement in a representative sample of 1177 Korean students over a five-year period from the 8 to 12th grades. Results indicated that the academic performance of students from the first semester of the 8th grade positively predicted self-efficacy beliefs for the second semester of the 8th grade and that self-efficacy beliefs from the second semester of the 8th grade positively predicted the academic achievement of students for the first semester of the 9th grade; this pattern evidenced through to the 12th grade. A reciprocal relationship between self-efficacy beliefs and academic achievement was seen, such that the effect of past academic performance on self-efficacy beliefs was larger than the effect of selfefficacy beliefs on academic achievement. These findings point to the importance of integrating the reciprocal model into practice and utilizing interventions delivered by educators, school counselors, and school psychologists that target both self-efficacy and academic achievement. Future research is needed to evaluate interventions designed to address both self-efficacy and academic achievement.

Predicting Academic Performance of Dental Students Using Perception of Educational Environment

Greater emphasis on student-centered education means that students' perception of their educational environment is important. The ultimate proof of this importance is its effect on academic performance. The aim of this study was to assess the predictability of dental students' grades as indicator of academic performance through their perceptions of the educational environment. The Dundee Ready Educational Environment Measure (DREEM) questionnaire was used to assess dental students' perceptions of their educational environment at the University of Dammam, Saudi Arabia, in academic year 2012-13. Aggregate grades in courses were collected at the end of the semester and related to levels of perception of the five DREEM domains using regression analysis. The response rate was 87.1% among all students in Years 2-6. As the number of students perceiving excellence in learning increased, the number of students with A grades increased. Perception of an environment with problems in the atmosphere and social life increased the number of students with D and F grades. There was no relation between any of the DREEM domains and past academic performance as measured by GPA. This study concludes that these students' academic performance was affected by various aspects of perceiving the educational environment. Improved perception of learning increased the number of high achievers, whereas increased perception of problems in atmosphere and social life increased the number of low achievers and failing students.

A Study on Sub-Clinical Narcissistic Personality Score and Its Relationship with Academic Performance-An Indian Experience

Sub-clinical narcissism is the presence of narcissistic personality traits in otherwise normal people. People with high levels of these traits said to have inflated self-esteem and possibly a high egotism. A 40 itemed Narcissistic Personality Inventory is used to measure this type of personality traits. Those individuals who score above 20 points from the available 40 points of NPI-40 Inventory is considered to be having higher levels of Subclinical Narcissism and prone to exhibit socially dislikeable personality traits. This study tried to address the relationship between supposedly negative personality traits of Sub-clinical Narcissism using NPI-40 Score against past and present academic performance of a group of students in a Private University setup. The study included 202 participants from a Business School Division of a Private University. Analysis showed that only at the current academic levels of the respondents, NPI-40 scores were significantly correlating with their academic performance. Research implications are discussed.