Predicting College Students Dropout using EDM Techniques

Anjana, Pradeep; Thomas, Jeena

doi:10.5120/ijca2015905328

Cited by 12 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using students' grades that are earned in quizzes and examinations have also been widely used in various studies for predicting students' academic success (e.g. Al luhaybi et al, 2018;Aulck et al, 2016;Badr et al, 2016;Huang & Fang, 2013;Kemper et al, 2020;Pradeep & Thomas, 2015;Shakeel & Butt, 2015;Villwock et al, 2015;Yadav et al, 2011;Yassein et al, 2017). Failure in examinations has also been used as a predictor; for instance, Kabakchieva ( 2013) used a dataset of 10,330 students to predict their performance using five classes (bad, average, good, very good, and excellent) and found that the number of failures at the first-year exams is among the most influencing features in the classification.…”

Section: Related Work On Predictions In Higher Educationmentioning

confidence: 99%

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Alturki

2021

JITE:IIP

View full text Add to dashboard Cite

Aim/Purpose: One of the main objectives of higher education institutions is to provide a high-quality education to their students and reduce dropout rates. This can be achieved by predicting students’ academic achievement early using Educational Data Mining (EDM). This study aims to predict students’ final grades and identify honorary students at an early stage. Background: EDM research has emerged as an exciting research area, which can unfold valuable knowledge from educational databases for many purposes, such as identifying the dropouts and students who need special attention and discovering honorary students for allocating scholarships. Methodology: In this work, we have collected 300 undergraduate students’ records from three departments of a Computer and Information Science College at a university located in Saudi Arabia. We compared the performance of six data mining methods in predicting academic achievement. Those methods are C4.5, Simple CART, LADTree, Naïve Bayes, Bayes Net with ADTree, and Random Forest. Contribution: We tested the significance of correlation attribute predictors using four different methods. We found 9 out of 18 proposed features with a significant correlation for predicting students’ academic achievement after their 4th semester. Those features are student GPA during the first four semesters, the number of failed courses during the first four semesters, and the grades of three core courses, i.e., database fundamentals, programming language (1), and computer network fundamentals. Findings: The empirical results show the following: (i) the main features that can predict students’ academic achievement are the student GPA during the first four semesters, the number of failed courses during the first four semesters, and the grades of three core courses; (ii) Naïve Bayes classifier performed better than Tree-based Models in predicting students’ academic achievement in general, however, Random Forest outperformed Naïve Bayes in predicting honorary students; (iii) English language skills do not play an essential role in students’ success at the college of Computer and Information Sciences; and (iv) studying an orientation year does not contribute to students’ success. Recommendations for Practitioners: We would recommend instructors to consider using EDM in predicting students’ academic achievement and benefit from that in customizing students’ learning experience based on their different needs. Recommendation for Researchers: We would highly endorse that researchers apply more EDM studies across various universities and compare between them. For example, future research could investigate the effects of offering tutoring sessions for students who fail core courses in their first semesters, examine the role of language skills in social science programs, and examine the role of the orientation year in other programs. Impact on Society: The prediction of academic performance can help both teachers and students in many ways. It also enables the early discovery of honorary students. Thus, well-deserved opportunities can be offered; for example, scholarships, internships, and workshops. It can also help identify students who require special attention to take an appropriate intervention at the earliest stage possible. Moreover, instructors can be aware of each student’s capability and customize the teaching tasks based on students’ needs. Future Research: For future work, the experiment can be repeated with a larger dataset. It could also be extended with more distinctive attributes to reach more accurate results that are useful for improving the students’ learning outcomes. Moreover, experiments could be done using other data mining algorithms to get a broader approach and more valuable and accurate outputs.

show abstract

Section: Related Work On Predictions In Higher Educationmentioning

confidence: 99%

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Alturki

2021

JITE:IIP

View full text Add to dashboard Cite

show abstract

“…ADT was used in 2 studies only. In the first study (Pal and Pal 2013), it produced 0.6950 accuracy, while in the second (Pradeep and Thomas 2015), it obtained an accuracy of 0.995 and was assessed as the best scoring method. CHAID was also used in two studies only.…”

Section: Mostly Used Data Mining Methods In Predicting Students' Achimentioning

confidence: 99%

Predicting Academic Outcomes: A Survey from 2007 Till 2018

2020

View full text Add to dashboard Cite

The tremendous growth of educational institutions’ electronic data provides the opportunity to extract information that can be used to predict students’ overall success, predict students’ dropout rate, evaluate the performance of teachers and instructors, improve the learning material according to students’ needs, and much more. This paper aims to review the latest trends in predicting students’ performance in higher education. We provide a comprehensive background for understanding Educational Data Mining (EDM). We also explain the measures of determining academic success and highlight the strengths and weaknesses of the most common data mining (DM) tools and methods used nowadays. Moreover, we provide a rich literature review of the EDM work that has been published during the past 12 years (2007–2018) with focus on the prediction of academic performance in higher education. We analyze the most commonly used features and methods in predicting academic achievement, and highlight the benefits of the mostly used DM tools in EDM. The results of this paper could assist researchers and educational planners who are attempting to carry out EDM solutions in the domain of higher education as we highlight the type of features that the previous researches found to have significant impact on the prediction, as well as the benefits and drawbacks of the DM methods and tools used for predicting academic outcomes.

show abstract

“…According to Rotem et al ( 2020 ), the conducted research regarding students' dropout and postponement at the undergraduate level is more than at the postgraduate level, and no solid predictive models are to be found for postgraduates. For instance, Alemu Yehuala ( 2015 ), Aulck et al ( 2017 ), Daud et al ( 2017 ), Pradeep and Thomas, ( 2015 ) and Shakeel and Butt ( 2015 ) predicted bachelor's degree drop out, Alturki and Alturki ( 2021 ), Pal and Pal ( 2013 ), Sembiring et al ( 2011 ), Yadav et al ( 2011 ) and Yadav and Pal ( 2012 ) predicted bachelor's students' academic achievement at a degree level, and Badr et al ( 2016 ), Huang and Fang ( 2013 ), Kovačić ( 2010 ) and Osmanbegović et al ( 2012 ) predicted bachelor's students' academic achievement at a course level. The above-mentioned researchers mostly used decision tree algorithms to perform their predictions.…”

Section: Literature Review On Predicting Students’ Academic Performancementioning

confidence: 99%

Predicting Master’s students’ academic performance: an empirical study in Germany

Alturki

Cohausz

Stuckenschmidt

2022

Smart Learn. Environ.

View full text Add to dashboard Cite

The tremendous growth in electronic educational data creates the need to have meaningful information extracted from it. Educational Data Mining (EDM) is an exciting research area that can reveal valuable knowledge from educational databases. This knowledge can be used for many purposes, including identifying dropouts or weak students who need special attention and discovering extraordinary students who can be offered lifetime opportunities. Although former studies in EDM used an extensive range of features for predicting students’ academic achievement (in terms of (i) achieved grades or (ii) passing and failing), those features are sometimes not obtainable for practical usage, and therefore, the prediction models are not feasible for employment. This study uses data mining (DM) algorithms to predict the academic performance of master’ s students by using a non-extensive data set and including only the features that are easy to collect at the beginning of a studying program. To perform this study, we have collected over 700 students' records from 2010 to 2018 from the Faculty of Business Informatics and Mathematics at the University of Mannheim in Germany. Those records include demographics and post-enrollment features such as semester grades. The empirical results show the following: (i) the most significant features for predicting students' academic achievements are the students’ grades in each semester (importance rate between 14 and 36%), followed by the distance from students’ accommodation to university (importance rate between 6 and 18%) and culture (importance rate between 7 and 17%). On the other hand, gender, age, the numbers of failed courses, and the number of registered and unregistered exams per semester are less significant for the predictions. (ii) As expected, predictions performed after the second semester is more accurate than those performed after the first semester. (iii) Unsurprisingly, models that predict two classes yield better results than those that predict three. (iv) Random Forest classifier performs the best in all prediction models (0.77–0.94 accuracy), and using oversampling methods to deal with imbalanced data can significantly improve the performance of DM methods. For future work, we recommend testing the predictive models on other master programs and a larger datasets. Furthermore, we recommend investigating other oversampling approaches.

show abstract

Predicting College Students Dropout using EDM Techniques

Cited by 12 publications

References 15 publications

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Using Educational Data Mining to Predict Students’ Academic Performance for Applying Early Interventions

Predicting Academic Outcomes: A Survey from 2007 Till 2018

Predicting Master’s students’ academic performance: an empirical study in Germany

Contact Info

Product

Resources

About