Predicting Student Academic Performance

The aim of this study is to undertake an empirical inquiry and comparison of the effectiveness of various classifiers with ensembles classifiers in the prediction of student academic performance. A single classifier algorithm will be compared against the performance and efficiency of ensemble classifiers. Reducing student attrition is a major problem for educational institutions all over the world. The search for solutions to increase student retention and graduation rates continues for educators. This is only possible if at-risk students are identified and intervened with as soon as possible. However, the majority of regularly used prediction models are inefficient and inaccurate as a result of inherent classifier limitations and the inclusion of insignificant inputs in their calculations. The majority of data mining and machine learning researcher focused on developing an algorithm that can extract useful information from massive amounts of data after being processed by a computer. The most difficult problem in predictive modelling is identifying the most effective prediction algorithms that are also accurate enough to be useful. Therefore, a multi-level homogeneous ensemble predictive (MLHoEP) model is designed, which uses the different techniques of data mining like feature selection, ensemble learning techniques like boosting and bagging. Seven distinct machine learning algorithms were used on this model to predict and analyse the academic performance of the students. The performance of the classification algorithms in terms of prediction was evaluated using k-fold cross-validation. The study contributes to the body of knowledge by suggesting the development of homogeneous classifiers that may be used to accurately predict students’ academic success. It also proposes the construction of homogeneous classifiers, which may be deployed for accurate student performance prediction, in order to provide a better explanation for the poor performance prediction. As a result of this research, it has been demonstrated that the technique of applying homogeneous ensemble approaches is incredibly efficient and accurate in terms of predicting student performance and assisting in identifying students, who are in danger of dropping out of school. The study compared the accuracy and efficiency of single classifiers to ensembles of classifiers in terms of performance. It was discovered in the research that a homogeneous model with excellent accuracy and efficiency might be developed for anticipating student performance. These key problems have been successfully addressed by the findings of this research study: Which characteristics of students are the most effective predictors of academic performance? How accurate are approaches such as bagging and boosting ensembles for predicting student academic performance? The approach offered in this study will aid educational administrators and policymakers in designing new policies and curriculum-linked to student retention in higher education. This research can also aid in the identification of students who are at risk of dropping out of school early, providing for timely intervention and support. Prospective research will examine the creation and implementation of an automated prediction system known as the students’ academic performance forecast framework, which will collect data from students via online submission and produce a prediction result for their academic performance.KeywordsEducational data miningEnsemble learningMultilayer perceptronRandom forestNaïve BayesCorrelation attribute evaluationInformation gainGain ratio

Predicting students’ academic performance is a crucial initiative in the field of education, as it allows educators and administrators to spot students who may require extra assistance, customize educational resources to meet individual requirements, and improve overall educational results. Conventional approaches to forecasting academic achievement, such as statistical analysis and expert evaluation, have certain drawbacks in terms of precision and scalability. The emergence of machine learning (ML) methods provides a possible alternative by utilizing extensive datasets and advanced algorithms to reveal patterns and generate more precise predictions. This investigation’s primary goal is to explore the predictive modelling of student academic performance by improving the accuracy of predictions through the utilization of machine learning techniques. The study was conducted utilizing the Python programming environment. The prediction of student academic performance was carried out utilising the Bidirectional long short-term memory (Bi-LSTM) based Weighted Cost Effective Random Forest algorithm. The study utilized the Deep Encoder CNN-Bi-LSTM for optimal feature extraction to foresee student academic performance. The extracted features were then classified using the Weighted Cost Effective Random Forest (WECRF) classifier, and the classification was evaluated in terms of accuracy, precision, specificity, sensitivity, and recall. The issues addressed include the class imbalance, computational complexity, cost, and huge dimensional issue, among others. The random forest method achieved Precision Score - 0.72, Recall Score - 0.68, F1 Score - 0.69, and Accuracy - 0.77 in this study. Moreover, the suggested technique facilitates the automated forecasting and enhancement of students' future academic performance. Keywords: Predictive Modelling; Students; Academic Performance; Machine Learning; Bi-LSTM; CNN-Bi-LSTM; Deep Learning.

Although most adolescents have access to smartphones, few of them use mobile health (mHealth) apps for health improvement, highlighting the apparent lack of interest in mHealth apps among adolescents. Adolescent mHealth interventions have been burdened with high attrition rates. Research on these interventions among adolescents has frequently lacked detailed time-related attrition data alongside analysis of attrition reasons through usage. The objective was to obtain daily attrition rates among adolescents in an mHealth intervention to gain a deeper understanding of attrition patterns, including the role of motivational support, such as altruistic rewards, through analysis of app usage data. A randomized controlled trial was conducted with 304 adolescent participants (152 boys and 152 girls) aged 13-15 years. Based on 3 participating schools, participants were randomly assigned to control, treatment as usual (TAU), and intervention groups. Measures were obtained at baseline, continuously throughout the 42-day trial period (research groups), and at the trial end. The mHealth app is called SidekickHealth and is a social health game with the following 3 main categories: nutrition, mental health, and physical health. Primary measures were attrition based on time from launch, and the type, frequency, and time of health behavior exercise usage. Outcome differences were obtained through comparison tests, while regression models and survival analyses were used for attrition measures. Attrition differed significantly between the intervention and TAU groups (44.4% vs 94.3%; χ21=61.220; P<.001). The mean usage duration was 6.286 days in the TAU group and 24.975 days in the intervention group. In the intervention group, male participants were active significantly longer than female participants (29.155 vs 20.433 days; χ21=6.574; P<.001). Participants in the intervention group completed a larger number of health exercises in all trial weeks, and a significant decrease in usage was observed from the first to second week in the TAU group (t105=9.208; P<.001) but not in the intervention group. There was a significant increase in health exercises in the intervention group from the fifth to sixth week (t105=3.446; P<.001). Such a significant increase in usage was not evident in the TAU group. The research group was significantly related to attrition time (hazard ratio 0.308, 95% CI 0.222-0.420), as well as the numbers of mental health exercises (P<.001) and nutrition exercises (P<.001). Differences in attrition rates and usage between groups of adolescents were identified. Motivational support is a significant factor for lowering attrition in adolescent mHealth interventions. The results point to sensitivity periods in the completion of diverse health tasks, and emphasis on time-specific attrition, along with the type, frequency, and time of health behavior exercise usage, is likely a fruitful avenue for further research on mHealth interventions for adolescent populations, in which attrition rates remain excessive. ClinicalTrials.gov NCT05912439; https://clinicaltrials.gov/study/NCT05912439.

Accurate prediction of student academic performance plays a vital role in enabling early intervention, adaptive instruction, and data-driven educational decision-making. However, the effectiveness of deep learning models such as Long Short-Term Memory (LSTM) networks is often constrained by suboptimal hyper-parameter tuning and insufficient exploration of the search space. To overcome these limitations, this paper introduces a novel hybrid learning framework, CNAE-LSTM, which integrates Chaotic initialization, a Niche-based evolutionary mechanism, and Alpha Evolution (AE) into a unified optimization paradigm termed Chaotic Niche Alpha Evolution (CNAE). Specifically, a chaotic operator is first employed to enhance population diversity during initialization; then a niche-based grouping strategy partitions the population into three subgroups with distinct mutation probabilities to preserve diversity and avoid premature convergence; finally, an Alpha Evolution mechanism guides the evolutionary search toward promising regions with improved exploration–exploitation balance. The proposed CNAE is utilized to optimize key LSTM hyper-parameters, including network architecture and training settings. Extensive experiments conducted on a real-world secondary education dataset demonstrate that CNAE-LSTM consistently outperforms conventional LSTM, SVM, CNN, Transformer models, as well as LSTM enhanced by QGA, QPSO, CWOA, QGWO, and grid/random search strategies. Results show that CNAE-LSTM achieves superior predictive accuracy, stability, and generalization capability, validating the effectiveness of the proposed hybrid framework for improving academic performance prediction.

BackgroundeHealth interventions can reach large populations and are effective in increasing physical activity (PA) and fruit and vegetable intake. Nevertheless, the effects of eHealth interventions are overshadowed by high attrition rates. Examining more closely when users decide to leave the intervention can help eHealth developers to make informed decisions about which intervention components should be reshaped or simply removed. Investigating which users are more likely to quit an intervention can inform developers about whether and how their intervention should be adapted to specific subgroups of users.ObjectiveThis study investigated the pattern of attrition in a Web-based intervention to increase PA, fruit, and vegetable intake. The first aim was to describe attrition rates according to different self-regulation components. A second aim was to investigate whether certain user characteristics are predictors for start session completion, returning to a follow-up session and intervention completion.MethodsThe sample consisted of 549 adults who participated in an online intervention, based on self-regulation theory, to promote PA and fruit and vegetable intake, called “MyPlan 1.0.” Using descriptive analysis, attrition was explored per self-regulation component (eg, action planning and coping planning). To identify which user characteristics predict completion, logistic regression analyses were conducted.ResultsAt the end of the intervention program, there was an attrition rate of 78.2% (330/422). Attrition rates were very similar for the different self-regulation components. However, attrition levels were higher for the fulfillment of questionnaires (eg, to generate tailored feedback) than for the more interactive components. The highest amount of attrition could be observed when people were asked to make their own action plan. There were no significant predictors for first session completion. Yet, two subgroups had a lower chance to complete the intervention, namely male users (OR: 2.24, 95% CI=1.23-4.08) and younger adults (OR: 1.02, 95% CI=1.00-1.04). Furthermore, younger adults were less likely to return to the website for the first follow-up after one week (OR: 1.03, 95% CI=1.01-1.04).ConclusionsThis study informs us that eHealth interventions should avoid the use of extensive questionnaires and that users should be provided with a rationale for several components (eg, making an action plan and completing questions). Furthermore, future interventions should focus first on motivating users for the behavior change before guiding them through action planning. Though, this study provides no evidence for removal of one of the self-regulation techniques based on attrition rates. Finally, strong efforts are needed to motivate male users and younger adults to complete eHealth interventions.

Real-Word Analysis of Clinical Characteristics and Outcomes Among Elderly Patients (pts) with Multiple Myeloma (MM)

Attrition in graduate surgical education: an analysis of the 1993 entering cohort of surgical residents

The paper by Pedersen & Skardhamar [1] is an excellent contribution to knowledge. They use data from the Young in Norway Longitudinal Study, which is an extremely important four-wave population survey. They show that cannabis use at ages 15 and 20 years predicts subsequent offending, but that the predictability is greater for drug crimes than for non-drug crimes. They also show that the predictability for non-drug crimes becomes non-significant after controlling for prior risk factors, alcohol intoxication and use of other illegal drugs. The analyses are neat and clear. While generally welcoming this excellent paper I wish to raise some issues, and I will divide these into ‘methodological’ and ‘substantive’. The most important methodological issue is attrition. According to Pedersen et al.[2], a nationally representative sample of seventh and eighth grade students was surveyed, using a self-administered questionnaire, in 1992–93. Of the original sample, 1.5% were excluded [at Time 1 (T1)] because of poor reading skills and 3.0% of the remainder were lost because of lack of student or parent consent or prolonged hospitalization. Of those who completed the T1 questionnaire, 91.6% completed the T2 questionnaire. According to Pedersen [3], of those who completed the T2 questionnaire, 90.4% consented to be followed-up further. Of those consenters, 84% provided data at T3 and 82% at T4 [1,3]. According to my estimate, about 65% of the original sample (98.5% × 97.0% × 91.6% × 90.4% × 82%) provided data at T4. Similarly, we are told that the cumulative response rate over all data collections was 69%, but this could possibly correspond to about 55% of the original sample. This is a good response rate for a mail follow-up study, but of course the problem is that those who are lost tend to be the high-risk students: male, with poor school grades, urban residence, and so on [1,3]. Commendably, Pedersen & Skarohamar estimate that the serious offending rate in their sample is about one-third less than in the population (7.8% compared to 11.6%, presumably up to age 27 years). However, the high and biased attrition rate may threaten the validity of the conclusions. In the Cambridge Study in Delinquent Development (CSDD), 411 London males have been followed-up from age 8 to age 48, using repeated personal interviews [4]. The attrition rate in this study was very low; the percentage of those still alive who were interviewed was 95% at age 18, 94% at age 32 and 93% at age 48. Importantly, the males who were the most difficult to interview were significantly more likely to be convicted [5], showing that conclusions about predictors of offending in studies with high attrition rates might be misleading. The second important methodological issue, which is related to some extent to the first, is that the number of offenders is low: only 5.1% at ages 15–20 and 3.5% at ages 20–27. This may make it difficult to obtain statistically significant results even if effect sizes are substantial. Although the male : female ratio for offending is high (5.3 : 1 at ages 20–27), males and females are combined in all the analyses, presumably because of the problem of small numbers. It is not clear to me why gender (and age) were not controlled in the Table 3 logistic regression analyses. The main conclusion of the paper is that cannabis use does not predict non-drug offending significantly after controlling for confounding factors. I am somewhat dubious about controlling for other drug use in model 3, because it could be argued that cannabis use and other drug use are both indicators of the same underlying construct. In the CSDD, there was a considerable overlap between cannabis and other drug users; the percentage of other drug users who were also cannabis users was 83% at age 18, 91% at age 32 and 64% at age 48. I will focus upon model 2. Here we see non-significant odds ratios (ORs) of the order of 2.0 for the relationship between cannabis use and non-drug offending. According to the Presidential Address by Cohen [6, p. 136], ‘the field of epidemiology tends to regard OR of 2.0 or more as fairly large’. A fairly strong relationship that is non-significant seems somewhat inconclusive to me, and not a very firm basis for the main conclusion of the paper that ‘the use of cannabis does not seem to represent a risk factor for a general criminal involvement’. The systematic review by Bennett et al.[7] was inconclusive in the opposite direction: the weighted mean OR for cannabis was a rather weak 1.5, but it was statistically significant (because it was based upon an accumulation of results obtained in 10 different studies). The main conclusion from the systematic review is that heroin, cocaine and crack were more strongly related to criminal behaviour than was cannabis. In the CSDD, cannabis use at age 18 significantly predicted non-drug convictions between ages 19 and 32 [39% of users were convicted, compared with 24% of non-users; OR = 2.0, confidence interval (CI) 1.3–3.3]. However, after controlling for prior convictions between ages 10 and 18 in a logistic regression, the prediction became non-significant (partial OR = 1.4), in agreement with the conclusions of Pedersen & Skarohamar [1]. Cannabis use at age 32 predicted non-drug convictions more strongly between ages 33 and 50 (31% of users were convicted, compared with 9% of non-users; OR = 4.5, CI 2.3–8.8). Furthermore, the significant predictability of cannabis use at age 32 held up after controlling for prior convictions at ages 10–18 and 19–32, heavy smoking, heavy drinking and binge drinking up to age 32, and age 8–10 risk factors that were the best predictors of non-drug convictions at ages 33–50. It may be that cannabis use predicts non-drug convictions more strongly at older ages than at younger ages, in agreement with findings in the systematic review by Bennett et al.[7]. Another issue that might be raised centres upon the validity of the self-report information. The fact that cannabis use predicts later drug charges might be cited as evidence of the predictive validity of the self-reports. A final problem is that both cannabis use and non-drug offending vary continuously as people grow older. In the absence of frequent repeated survey information, it is difficult to investigate whether cannabis use has any causal effect on non-drug crime. Ideally, it would be desirable to investigate whether changes in cannabis use within individuals were followed reliably by changes in non-drug offending within individuals, after controlling for confounding factors. To conclude, the paper by Pedersen & Skardhamar [1] reports interesting and thought-provoking results from a very important prospective longitudinal survey of drug use and offending. Many more surveys of this kind are needed, with large samples, low attrition and frequent data collection. None.

Attrition from training is associated with substantial financial and personnel loss. There is a plethora of medical literature and research of attrition rates related to initial/phase 1 training (basic combat training); however, the analysis of second phase training (commanders training, consisting of schools that qualify junior commanders and officers for infantry and non-infantry combat units) is limited. The purpose of this study is to perform a comprehensive survey regarding to medical attrition from commanders training in the IDF (Israeli Defense Forces) in order to present the commanders of the IDF a detailed situation report that will serve as an evidence-based platform for future policy planning and implementation. A cross-sectional study including all soldiers (23,841) who participated in commanders training in the IDF in the period of 2012-2015 was performed. Soldiers for whom the attrition reason (medical or not medical) was missing were excluded from this study. Data were collected from the adjutancy-computerized system as well as the IDF's computerized medical consultation records package (CPR). Descriptive statistics were performed using mean, standard deviation, and median in order to express results. For the determination of statistical significance, chi-square test, Student's t-test, and Poisson regression models were used. Out of 23,841 soldiers that participated in this study, 75% (17,802) were males and 25% (6,039) were females. The overall attrition rate was 0.7% (164). The attrition rate for males was 0.86% (148 out of 17,082 males) and 0.26% (16 out of 6,039 females) for females. After adjusting for training unit, age, and BMI, the risk for attrition was 1.6 (160%) times higher for males as compared with females, and this result was statistically significant (IRR = 1.6, p = 0.01, CI 1.1, 2.2). The re-injury rate was 41% (68 out of 164 soldiers). The three most frequent diagnoses for attrition were orthopedics (66%), general surgery diagnoses (12%), and diagnoses related to internal medicine (11%). Out of 107 soldiers that attired due to orthopedic reasons, 36 (34%) suffered from calf and ankle injuries, 22 (21%) attired due to diagnoses related to the lower back, and 22 (21%) attired due to diagnoses related to the knee region. The highest attrition rate was encountered in the school for infantry junior command (2.2%) and the lowest rate was encountered in the officer training school for non-infantry units (0.11%). After adjusting for age and BMI, the risk for ankle injury was 2.55 (255%) times higher for soldiers in the school for infantry junior command as compared with soldiers in the officer school for infantry units (IRR = 2.55 p = 0.017, CI 1.18, 5.47). The attrition rate from commanders training in the IDF is low, and at this point, however, due to lack of uniform criteria for attrition, it cannot serve as an objective measure. We suggest measuring and discussing overuse injury rates (which is the most frequent cause of attrition), instead. Based on our results, we recommend an implementation of a better medical screening policy in order to reduce the re-injury rates during commanders training.

Introduction: Educational Data Mining and Machine Learning Models gained more interest among researchers and academicians in recent years. These are used to extract meaningful data from the educational database can be applied to predict the student academic performance. Objective: The main objective of this research shows the capability to predict the student's performance and is highly beneficial to take remedial actions in the present educational system. It also offers suitable student assistance, allows an educational institution or teacher to help the students in gaining extra marks. Methods: The presented model operates in two stages, namely classification and outlier detection. Initially, a multilayer perceptron is employed for data classification. Later, a stochastic gradient descent classifier and multi-layer perceptron are integrated to effectively classify the data. For further improvement in the classification, Student academic performance, outlier detection method namely radial basis function is applied to remove the misclassified instances. Results: The proposed model achieves superior classification performance with the maximum precision of 79.30, recall of 79.30, and accuracy of 79.30, F-score of 79.30 and kappa value of 52.40 respectively. The simulation outcome exhibited that the multilayer perceptron and stochastic gradient descentmodel offers better results over the other classifiers. However, the usage of outlier detection using the radial basis function model takes the classifier results to the next level. Conclusion: Using classification techniques a new student academic performance model is proposed by addressing some issues in the existing model which is used to predict the student academic performance assist inproper time.

This study traces the development of the Indian IT sector from TCS's founding in 1967 to its emergence as a multibillion-dollar sector in 2023. Many IT firms were set up in India after the establishment of the firm TCS with Tier 1 and Tier 2 categories, based on their size, revenue, and other factors., etc. Analyzed are two of the issues of the IT sector: a high attrition rate and low employee engagement. The reasons behind these are identified, and a methodology is created to raise employee satisfaction and lower the attrition rate in the Indian IT industry. News articles in publications including Times of India, Hindustan Times, Deccan Herald, Economic Times, and LiveMint provided information about the Indian IT industry. Google Scholar provided keywords such as "Indian IT Sector," "Employee Motivation," "Employee Engagement," "Job Satisfaction," and "Attrition." For every keyword searched from 1980 to 2022, the top 20 referenced papers were found. A total of 77 publications were reviewed, and their abstracts were examined to determine their applicability to the study question. Additionally, a number of OB and HRM textbooks were searched for information about the keywords. Definitions of motivation, employee engagement, job satisfaction, and attrition rate that are pertinent to the research study are created from a systematic literature analysis, giving these concepts more conceptual clarity. A model that connects attrition rate, job satisfaction, employee engagement, and motivation is built. Theoretical inferences of the model are examined, including the inclusion of individual characteristics, organisational commitment, and turnover intentions. The model's practical implications, such as its application in the business world and in nations with different cultural norms, are examined. Lastly, a discussion of the study's limitations is included, as the model was created using a limited number of variables.

In recent years , research evolution in domain of education focus on analytics and which provides insights on students academic performance. The tremendous growth of instructional institutions’ electronic information provides the chance to extract info which will be wont to predict students’ overall success, predict students’ dropout rate, appraise the performance of academics and instructors, improve the learning material in step with students’ desires, and far a lot of. This paper aims to review the latest trends in predicting students’ performance in educational activity. we explain the measures of determinant educational success and highlight the strengths and weaknesses of the foremost common data processing (DM) tools and strategies used today. Moreover, we offer a fashionable literature review of the EDM work that has been revealed during the past years with target the prediction of educational performance in educational activity. we tend to analyze the foremost normally used options and strategies in predicting educational accomplishment, and highlight the advantages of the principally used DM tools in EDM. The results of this paper might assist researchers who are working to hold out EDM solutions within the domain of education as we tend to highlight the type of options that the previous researches found to possess important impact on the prediction, likewise because the edges and downsides of the DM strategies and tools used for predicting educational outcomes.

Educational institutes carried out a huge research to investigate student academic performance and analyses the major factors that may affect student performance. Educational institutes care about how many students will continue their studies successfully and their appreciation. There is a crucial need to investigate and address the main challenges that may affect the student academic performance. In this paper, we propose a new approach to analyses student academic performance using Gradient Boosting algorithms. In particular, the proposed approach implements the XGBoost, CaBoost and LighGBM Gradient Boosting algorithms. The proposed approach consists of two prediction models: the student final status model and student appreciation model. The achieved results show that the CaBoost algorithm gets the best prediction results when it reaches 92.16% for student final status model and 86.89% for student appreciation model. On the other hand, the LightGBM gets the best results in terms of speed.

A significant attrition rate among doctoral students has increased attention in the past two decades. Different researchers have identified factors contributing to doctoral programs' attrition rate. Although exploring these external factors contributes to the retention of doctoral students, only a few studies have explored the internal factors that contribute to the retention of doctoral students. This study aimed to explore the internal factor, self-compassion, in reducing distress, anxiety and depression that causes higher attrition rates among doctoral students. The study was descriptive, while correlational research was used to establish the relationship between self-compassion and emotional well-being. For this study, a sample of 80 doctoral students, through multistage sampling, from 3 selected universities were selected for the study. Two questionnaires, i.e. Self-Compassion Scale and DASS-21, were used to collect data. The finding revealed a higher association between self-compassion and emotional well-being. It was observed that a greater level of self-compassion resulted in a lower level of emotional well-being. It indicated a significant negative relationship between self-compassion and the emotional well-being of doctoral students. Interventions for improving the level of self-compassion may enhance overall well-being. This will ultimately be supportive in reducing depression, anxiety and stress among doctoral students, which will result in better retention among doctoral students in Punjab.

With the advent of 21st century the call centers have become an important auxiliary service centers to many business organizations. High level of attrition rate hampers the growth of call center industry. This study attempts to understand the reasons behind the high attrition rate in Indian call center industry. Results of regression analysis reveal that among various hypothesized determinants of attrition, “job insecurity” and “Low Promotional Chances” significantly contribute to high attrition rate in call centers. On the basis of results of this study some suggestions have been put forth for the minimization of attrition levels in call centers.