Student Dropout Research Articles

Predicting Student Dropout Rates in Higher Education: A Comparative Study of Machine Learning Algorithms

Recent years have seen a significant increase in study interest in the areas of predicting student performance, avoiding failure, and identifying the variables affecting student dropout. One important indicator in online and open distance learning courses is the student dropout rate. We purpose the naive bayes classification method to construct the student dropout prediction using naive bayes. This work examines the critical topic of forecasting student dropout rates in higher education using machine learning approaches, with a particular emphasis on the random forest algorithm and the naive bayes algorithm. The study's goal is to properly anticipate dropout rates using data mining methods and machine learning algorithms after conducting a thorough evaluation of existing literature and approaches. The systematic method consists of data collection from a Kaggle dataset, data preparation to solve class imbalance via SMOTE oversampling, and algorithm selection. Random forest and naive Bayes approaches outperform other machine learning algorithms in terms of accuracy, sensitivity, specificity, and precision. The study underscores the importance of considering diverse factors such as demographic data, socioeconomic factors, and academic performance in dropout prediction models. The implications of this research extend beyond academia, with the potential to inform proactive interventions and support systems, ultimately leading to improved student outcomes and institutional effectiveness. According to this paper, the paper outputs that for the binary classification on the data set used in this project has best performed with Naive Bayes and Random Forest Algorithm with SMOTE oversampling. Keywords- SMOTE oversampling, machine learning, Random forest, naive bayes.

Student Dropout: A Bibliometric Analysis of Influencing Factors Using VOS Viewer to Explore Trends, Impact, and Collaborative Patterns

This article presents a bibliometric review of academic research on student dropout. The aim is to identify trends, evaluate the impact of publications, and examine collaboration patterns within this field. The SCOPUS database is utilized to identify and classify the most relevant research based on journals, articles, authors, institutions, and countries. Additionally, VOSviewer software is employed to map the bibliographic material, using co-citations and keyword co-occurrence for scientific mapping. The results indicate a significant increase in the number of publications over a 10-year period, reflecting a growing interest in the topic. Citation analysis reveals that certain key articles have had a substantial impact, being frequently cited in subsequent work. It is also observed that researchers with publications in Q1 and Q2 ranked journals have made significant contributions to the literature, marking a strong influence in the field. In terms of collaboration, there is an increase in international partnerships, with a growing number of publications co-authored by researchers from different countries. Leading institutions in student dropout research include universities in the United States, Europe, and Latin America, noted for their high scientific output and influence on the topic. This bibliometric analysis not only provides a detailed view of trends and the impact of research on student dropout but also highlights the importance of international collaboration in advancing knowledge in this field. Received: 29 July 2024 / Accepted: 23 October 2024 / Published: 05 November 2024

Artificial intelligence in management education: transformative potential and challenges

Purpose The purpose of this paper is to define artificial intelligence (AI) and examine its history, positive and negative impacts, ethical and social implications and implementation within management education. This paper offers various suggestions for the use of AI, as well as context surrounding the current AI landscape. Design/methodology/approach The paper uses a narrative review (Sylvester et al., 2013). Findings This paper identifies several areas of AI innovation, including AI tutoring systems, feedback systems for student papers, utilization of AI for innovative lesson plans and the use of AI to predict potential student dropout from a course or institution. In addition, there are significant concerns regarding the lack of ethical guidelines with current AI. Practical implications Practical implications include the ability to immediately use certain AI tools to enhance lesson plans as well as enhance student work using AI as a tool. Originality/value This paper was originally created as a conference presentation and presented at the society for advancement of management (SAM) International Business Conference before being reworked to be submitted to the journal. All content in this paper is original in their creation.

A multivariate analysis of the early dropout using classical machine learning and local interpretable model-agnostic explanations

Student dropout rates can have a significant negative impact on both the development of educational institutions and the personal growth of students. Consequently, many institutions are focused on identifying key factors that contribute to dropout and implementing strategies to mitigate them. This study aims to predict student dropout rates using classical machine learning algorithms while analyzing the key factors influencing these outcomes in higher education. The dataset includes demographic, socioeconomic, and academic information from various sources. Additionally, the study leverages the Local Interpretable Model-Agnostic Explanations (LIME) model to provide insights into the predictions, offering a clearer understanding of the factors driving dropout decisions. This knowledge is crucial for identifying influential factors and, more importantly, enhancing early intervention strategies and policies in educational settings, ultimately reducing dropout rates.

A Novel Predictive Modeling for Student Attrition Utilizing Machine Learning and Sustainable Big Data Analytics

Student attrition poses significant societal and economic challenges, leading to unemployment, lower earnings, and other adverse outcomes for individuals and communities. To address this, predictive systems leveraging machine learning and big data aim to identify at-risk students early and intervene effectively. This study leverages big data and machine learning to identify key parameters influencing student dropout, develop a predictive model, and enable real-time monitoring and timely interventions by educational authorities. Two preliminary trials refined machine learning models, established evaluation standards, and optimized hyperparameters. These trials facilitated the systematic exploration of model performance and data quality assessment. Achieving close to 100% accuracy in dropout prediction, the study identifies academic performance as the primary influencer, with early-year subjects like Mechanics and Materials, Design of Machine Elements, and Instrumentation and Control having a significant impact. The longitudinal effect of these subjects on attrition underscores the importance of early intervention. Proposed solutions include early engagement and support or restructuring courses to better accommodate novice learners, aiming to reduce attrition rates.

A Conceptual Model for Understanding the Factors Influencing Student Retention in Higher Education Institutions Offering Foreign Degrees during Sri Lanka's Economic Crisis

In early 2020, Sri Lanka faced the COVID-19pandemic, which led to nationwide lockdowns. These lockdowns exacerbated an economic crisis, resulting in wide spread job losses across various sectors, including higher education. The higher education sector in Sri Lanka is divided primarily into state universities and private institutions offering foreign degrees. The government funds state universities, and education is typically free for students, while private institutions that offer foreign degrees charge tuition fees. During the economic crisis, authorities observed a significant increase in student dropouts from these private institutions. Additionally, many students considered discontinuing their studies after completing their current courses. Although administrators implemented several immediate measures to address this issue, many of these efforts were unsuccessful, as the underlying reasons for the dropouts were not thoroughly investigated. While some research has been conducted to understand student dropouts, few studies have focused on the factors influencing educational continuation in the context of an economic crisis.

Self-Perceived Reasons to Dropout from Higher Education - a Case Study in a Portuguese Faculty of Engineering

Abstract : Dropout from Higher Education (HE), that is, the number of students that totally leave a given HE institution is concerningly high, especially in times of crisis. Institutions struggle to minimize dropout, but limited data is available likely because gathering data from learners who dropped out is sensitive, likely involving private information. This paper presents a case study research on student dropout from a very large Portuguese engineering faculty. The main objectives of this research include to gain a better understanding about the reasons for dropout, from the former student’s point of view, and to build a profile for the dropout-at-risk student. The collected data was retrieved from institutional records and from 134 telephonic interviews with former students. The resulting data is analysed in both quantitative and qualitative ways. Results of all gathered dropout data are clustered into three profiles of students who dropout: those that “pull out”, those who were “pushed out” and those who “fall out”. Findings include that students do not decide to dropout by a simple single reason but rather a set of reasons. This research article includes 5 concrete improvement suggestions that are likely to reduce dropout. The two main suggestions are to better prepare the transition to HE and to make policies more flexible in times of crisis, example more flexible schedule. Keywords: dropout; Higher Education; reasons to dropout.

Examining Dropout Among Graduate and Undergraduate Public Affairs and Political Science Students

Within the domain of public affairs and political science (PAPS), student dropout emerges as a critical concern. This study delves into the factors influencing the decisions of undergraduate and graduate PAPS students to discontinue their programs. Employing a comprehensive mixed-methods approach, we surveyed 384 at-risk undergraduates and conducted in-depth interviews with 18 former graduate students. Thematic analysis of these interviews revealed six pivotal factors influencing graduate student dropout: the financial burden of study (including tuition and limited financial aid), program curricular challenges (such as demanding thesis requirements and inadequate practical components), the delicate balance of multiple responsibilities (work, study, and family), health-related issues (including anxiety and stress), poor academic performance, and personal difficulties (such as lack of family support). At the undergraduate level, descriptive analyses indicated that 38% of PAPS students contemplated dropping out, with 30% considering changing their major. Exploratory Factor Analysis and Multiple Regression highlighted the significance of factors such as family and societal influences, economic considerations, program and curriculum structure, institutional dynamics, academic performance, personal attitudes, and student health in shaping these contemplations. This research not only expands the application of integration and engagement theory and the pull, push, and failing out theory but also validates their effectiveness in predicting dropout within PAPS programs. The study offers valuable insights for both researchers and policymakers, underscoring the imperative for more supportive, flexible, and financially viable educational structures to enhance student retention in the realm of public affairs and political science.

Affirmative Action for Black, Indigenous and Quilombola Students at a Brazilian University

Multiculturalism and cultural diversity permeate various sectors of society, including higher education. The educational policies implemented in this sphere appear to promote social and educational equality. The aim of this study was to examine this subject by analysing the affirmative action policy implemented in a Brazilian university. It sought to understand whether this policy has contributed to the access and completion of undergraduate programmes of black and mixed-race, indigenous and quilombola students. The analysis was conducted based on data relating to the access and dropout of students who enrolled in the university through the quota and reservation systems. Data were collected from university administrative datasets and a questionnaire administered to undergraduate course coordinators and students who had benefited from the policy in question and dropped out of university. The findings reveal, on the one hand, an increase in the intake of black and mixed-race, indigenous and quilombola students. On the other hand, a high dropout rate was observed among these students, which may raise the possibility that the policy in question is not completely successful.

The Cause of Student Dropout from TVET at Malaysia Industrial Training Institute

The Cause of Student Dropout from TVET at Malaysia Industrial Training Institute

Cohort Survival of the K to 12 Student Entrants Towards the Development of Strategic Interventions Supportive to Cbea-mmsu Programs

The study was undertaken to determine the cohort survival rate of the pioneer batch of the K to 12 student entrants of the eight (8) degree programs at the College of Business, Economics and Accountancy (CBEA), identify the underlying factors triggering the student dropout and institutionalize an intervention program to support the successful retention and graduation of all students. The Reconstructed Cohort Method was used and places less demand on the availability of detailed data over time. This method makes three assumptions: dropouts never return to school; the promotion, repetition and drop-out rates observed in the last two years remain constant over the entire period in which the cohort is enrolled in school and the same rates apply to all students enrolled in a given year level, regardless of whether they previously repeated a subject. A comprehensive analysis on the data gathered was done to process the underlying factors which will serve as valuable inputs in the design of programs and policies to reduce the dropout rate and support the successful retention and graduation of students. Findings showed that the survival rate of the pioneer batch of the K to 12 student entrants of the different programs range from 55.5% (BS Accountancy) to 97.5% (BSBA HRM) or an average of 81.62%. Overall, the survival rate among the males is 84.14% and the females is 80.86%. Majority (81.03%) of the respondents who were not able to finish their schooling on time indicated academic-related as their reason. Others mentioned about personal/family concern (17.24) and one indicated career concern. Some of the suggested interventions supportive to CBEA programs include: the implementation of an institutionalized Academic Advising Program, conduct of series of Academic Advising workshop, Academic Counseling, referral, group counselling, a more aggressive admission interview, parent/guardian conference, peer tutorial, financial assistance program and documentation of academic advising and counseling sessions. In addition, Guidance counselors must be one of the signatories in the dropping out and shifting forms. A replication research study involving different programs in the university is recommended.

Factors Affecting Students Dropout as Perceived by the Senior High School Students of MSU Marawi City. A Basis for a Proposed Guidance and Counseling Intervention Program and School Community Partnership

This study aimed to determine the Factors affecting Students Dropout as Perceived by the Senior High School Students of MSU Marawi City. A Basis for a Proposed Guidance and Counseling Intervention Program and School Community Partnership. This study undertaken to highlight the answers of the following questions. First, what is the profile of the respondents in terms of Age, Gender, Civil Status, Religion, Affiliation, Ethnicity, Scholarship, Number of Siblings, Siblings Rank. The Father’s Educational Attainment, Father Occupations, Mothers Educational Attainment, Mother’s Occupation and Family Monthly Income. Second, what are the causes and factors affecting drop out in school among the graduating students of Senior High School of MSU Marawi City in relation to the following, Family Related factors, Peers Related Factors, School Related Factors Personal Problems Related Factors, Peace and Order and Ridu. Third, what is school community partnership and intervention program may be formulated based on the findings of the study. This study was conducted in MSU Marawi City Senior High School where three hundred forty-one students served as the respondents. A descriptive design was used in this study. SelfConstructed questionnaire was the main instrument used to gather data for this study. After administering, recording, tabulating and interpreting the data gathered the following finding were drawn: Many (41.64%) of the respondents were between 18 to 20 years of age, (56.89%) of the respondents were female, Majority (64.81%) of them belong to Islam religion. Majority (57.77%) were Meranao. Therefore, Senior High School of MSU Marawi City has an age of brackets of 18 to 20 years old, a female, with a religious affiliation of Islam, a Meranao, and ESC Grantees status, with 6 or more siblings, probably 3rd or 5th in rank, where father’s and mother’s Educational Attainment is college graduate both working in government office with a monthly income of above P 15, 000.00 The researcher observed that the factors related to students dropout was Ridu (3.11%) and peace and order ( 2.77%) family (2.76%) personal( 2.73%) peer ( 2.73%) and School (2.72) were sometime related to students’ dropout in school. As such, there is no one causes and factor that could contribute to dropouts of the students. Studies yielded that no single factor can completely account for student’s performance and decision to continue in school until they finish their senior high school. Just as a student they report a variety of reasons for not pursuing their academic. The decision to drop out is not simply a result of what happens in school. Clearly student’s behavior and performance in school influences their decision to stay or leave, but students’ activities and behaviors outside of school particularly engaging in deviant behavior also influences their determination to pursue their academic. Thus, this study is primarily recommended to the school heads, curriculum makers, guidance counselor, parents, community, teachers, students and to the future researchers to really assess, properly monitor the students’ performance will help them focus their studies and pursue to graduate. The benefits of this study greatly help in motivating the students to stay in school and graduate. Planning and decision making should consider the background knowledge, and culture of the students prior to his needs.

Tutorial action models in universities of Latin America: A systematic review

Introduction: University tutorial action is a process of student intervention framed within educational orientation, and inherent to teaching action, increasingly considered in Latin America, as an effective strategy that reduces student dropout, and increases. the completion of university studies.Objective: Identify the main characteristics of the tutorial action models implemented in universities in Latin America.Methods: A systematic exploratory review of the existing updated literature, published in the last five years in the Web of Science and Google Scholar databases, referring to the Latin American context, was carried out.Results: A total of 21 studies considered relevant to the research were analyzed.Conclusions: It is evident that in the region there are different positions regarding the conception, organization and implementation of the tutorial action. The terms models, project and tutorial action plan are used interchangeably to represent the tutorial action as an object. just as the declared foundations appear imprecisely.

Risk factors for student dropout in higher education institutions in latin america

Introduction: In Latin America, university dropouts significantly influence the individual development of students and the socioeconomic progress of the region. Identifying risk factors allows educational institutions to recognize and address the specific needs of their students to create effective methods that foster academic success and retention. Objective: Analyze the various risk factors for student Dropout in Higher Education Institutions in Latin America with the purpose of proposing strategies that reduce the negative rates of this problem. Methods: A bibliographic review of studies published between 2010 and 2024 on risk factors for student dropout in higher education in Latin America was carried out, using relevant databases and applying rigorous inclusion and exclusion criteria. Results: Personal, academic, institutional and socioeconomic variables are part of the risk factors for University Dropout. The lack of access to Higher Education has a significant impact on the economic and social growth of Latin America since it is essential for the training of qualified professionals. The high dropout rate contributes to a less prepared workforce and limits job opportunities for young people. Conclusions: The prevalent risk factors were academic and personal associated with university dropout in Latin America, which is why various strategies were proposed to generate inclusive and equitable higher education through the reformulation of public and institutional policies.

A MERN based Web Application for Analysing Student Dropout

The technological advancement has led to the rapid changes in education system, enhancing the student’s engagement and improving personalized education. However, one major challenge that is faced by the school is students leaving before completing their courses. The proposed system aims to address this issue by identifying the various factors that lead to the student dropouts. The user-friendly website developed in the proposed work allows both students and educational institutions to provide the reasons for student dropouts. The system is designed to analyse the collected data, extract valuable information, and identify hidden patterns. These insights are then presented as visuals, such as charts and graphs, to help better understand the underlying causes of dropouts. The primary objective of the proposed system, developed using MERN, is to create a more inclusive and supportive learning environment that focuses on both student academic achievement and safety. Ultimately, this system aims to reduce dropout rates and improve access to quality education for all students, regardless of their background or circumstances.

On Use of eXplainable Artificial Intelligence to Explain Student Dropout

On Use of eXplainable Artificial Intelligence to Explain Student Dropout

Predicting Student Dropout Rates Using Supervised Machine Learning: Insights from the 2022 National Education Accessibility Survey in Somaliland

High student dropout rates are a critical issue in Somaliland, significantly impeding educational progress and socioeconomic development. This study leveraged data from the 2022 National Education Accessibility Survey (NEAS) to predict student dropout rates using supervised machine learning techniques. Various algorithms, including logistic regression (LR), probit regression (PR), naïve Bayes (NB), decision tree (DT), random forest (RF), support vector machine (SVM), and K-nearest neighbors (KNN), were employed to analyze the survey data. The analysis revealed school dropout rate of 12.67%. Key predictors of dropout included student’s grade, age, school type, household income, and type of housing. Logistic regression and probit regression models highlighted age and student’s grade as critical predictors, while naïve Bayes and random forest models underscored the significance of household income and housing type. Among the models, random forest demonstrated the highest accuracy at 95.00%, indicating its effectiveness in predicting dropout rates. The findings from this study provide valuable insights for educational policymakers and stakeholders in Somaliland. By identifying and understanding the key factors influencing dropout rates, targeted interventions can be designed to enhance student retention and improve educational outcomes. The dominant role of demographic and educational factors, particularly age and student’s grade, underscores the necessity for focused strategies to reduce dropout rates and promote inclusive education in Somaliland.

The Use of Deep Learning in Open Learning: A Systematic Review (2019 to 2023)

No records of systematic reviews focused on deep learning in open learning have been found, although there has been some focus on other areas of machine learning. Through a systematic review, this study aimed to determine the trends, applied computational techniques, and areas of educational use of deep learning in open learning. The PRISMA protocol was used, and the Web of Science Core Collection (2019–2023) was searched. VOSviewer was used for networking and clustering, and in-depth analysis was employed to answer the research questions. Among the main results, it is worth noting that the scientific literature has focused on the following areas: (a) predicting student dropout, (b) automatic grading of short answers, and (c) recommending MOOC courses. It was concluded that pedagogical challenges have included the effective personalization of content for different learning styles and the need to address possible inherent biases in the datasets (e.g., socio-demographics, traces, competencies, learning objectives) used for training. Regarding deep learning, we observed an increase in the use of pre-trained models, the development of more efficient architectures, and the growing use of interpretability techniques. Technological challenges related to the use of large datasets, intensive computation, interpretability, knowledge transfer, ethics and bias, security, and cost of implementation were also evident.

Aligning Strategies of Institutes with Student Expectations: An Exploration of External Factors Shaping Students' Choice of Private Higher Education Institutes

Student enrollment and retention are critical aspects of the economic sustainability of a private higher education institute (HEI). However, due to the growing number of private HEIs worldwide, huge competition has been created among these institutes. This has resulted in institutes investing heavily in ineffective strategies because they are implemented without fully understanding student expectations. Due to this, student dropouts can also be observed. Failure to meet enrollment targets and dropouts not only creates revenue loss but also negatively affects the reputation of the HEIs, impacting the viability of the institute. Therefore, much interest has been generated in identifying the factors that motivate students when choosing an HEI. This study’s main aim is to conduct a review of the available literature and identify the external factors, namely HEI-related characteristics and the communication methods that influence students when choosing a private HEI that directly impact the institutes. The inclusion criteria for the chosen literature consisted of studies conducted on the motivational factors of undergraduates and high school students who were in the process of choosing an HEI. The literature reviewed shows that students are influenced by HEI-related characteristics such as the reputation of the HEI, course fees, facilities offered, employability of graduates, academic quality, and quality of faculty and by the information gathered through communication methods such as websites and social media advertisements. HEIs can consider these findings to develop policies, improve their facilities and activities, and formulate and implement marketing strategies through the communication channels identified in this study.

Unveiling Dropout Patterns: A Python-Powered Analysis of Student Attrition in School Education

Student dropout rates pose a significant challenge in Gujarat, India, affecting both societal welfare and economic development. This study aims to diagnose and predict student dropout patterns using data analytics and machine learning (ML) algorithms. Extensive datasets from Gujarat's educational authorities are preprocessed with Python libraries such as Pandas and NumPy, ensuring quality and consistency. Exploratory data analysis (EDA) uncovers insights and trends, while feature engineering extracts relevant characteristics for ML models. The study implements ML algorithms Random Forest (RF), Decision Trees (DT), Logistic Regression (LR), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Machine(SVM) to construct predictive models. The findings reveal critical factors influencing dropout rates and assess model performance using model accuracy. This research provides novel insights into student dropout rates in Gujarat, offering a comprehensive, data-driven approach to address educational attrition and guide targeted intervention strategies and policy recommendations for improving educational outcomes in the region.