Early dropout prediction using data mining: a case study with high school students

Márquez-Vera, Carlos; Cano, Alberto; Romero, Cristóbal; Noaman, Amin Y.; Fardoun, Habib M.; Ventura, Sebastián

doi:10.1111/exsy.12135

Cited by 219 publications

(140 citation statements)

References 37 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…at first 4 and 6 weeks of the course. They also purposed a new ICRM2 algorithm which outperformed all other classification algorithm used till date [21].…”

Section: Recent Work Done On Predicting Educational Dropoutmentioning

confidence: 99%

Literature Survey on Educational Dropout Prediction

Kumar¹,

Singh²,

Handa³

2017

IJEME

View full text Add to dashboard Cite

Educational Data Mining (EDM) is one of the crucial application areas of data mining which helps in predicting educational dropout and hence provides timely help to students. In Indian context, predicting educational dropouts is a major problem. By implementing EDM, we can predict the learning habits of the student. At present EDM has not been introduced at higher education level. Due to this we cannot recognize the genuine problems of students during their education. The objective of this analysis is to find the existing gaps in predicting educational dropout and find the missing attributes if any, which my further contribute for better prediction. After that we try to find the best attributes and DM techniques which are frequently used for dropout prediction. Based on the combination of missing attribute and best attribute of student data thus far, a new algorithm can be tested which may overcome the shortcomings of previous work done.

show abstract

“…at first 4 and 6 weeks of the course. They also purposed a new ICRM2 algorithm which outperformed all other classification algorithm used till date [21].…”

Section: Recent Work Done On Predicting Educational Dropoutmentioning

confidence: 99%

Literature Survey on Educational Dropout Prediction

Kumar¹,

Singh²,

Handa³

2017

IJEME

View full text Add to dashboard Cite

show abstract

“…Another related work in [6] using MATLAB 2015b platform [18], the authors perform prediction and classification from graduated student data recorded between 2007 and 2011 in the Computer Science (CS) department at Faculty of Science and Technology, Sakon Nakhon Rajabhat University, Thailand. Two models for the 3 rd year and 4 th year have been constructed to predict grades results by applying Neural Network algorithm [26] and seven classes of students who had similar grade pattern in each course have been obtained using the clustering technique namely K-means algorithm [12].…”

Section: Related Workmentioning

confidence: 99%

Finding Most Effective Sequences of Modules for Students in Higher Education to Improve their Performance using Knowledge Discovery in Databases

Bousbahi¹

2017

IJCA

View full text Add to dashboard Cite

Universities offer a wide selection of courses to students studying in different fields; however, this has generated various unintended problem such as students struggling, dropping or failing. Universities also, own large amounts of historical data about students containing rich knowledge that can be used to facilitate a broad range of educational research and analytics study in order to enhance student performance. Knowledge discovery in databases (KDD) is the process of finding comprehensible patterns that can be interpreted as useful or interesting knowledge. One component in this process is Data Mining which is the application of machine learning algorithms for extracting patterns from data. In this context, data mining techniques are used to answer educational research questions that highlight students" success in higher education. Several challenges are facing higher education, one of which is finding the most effective sequence of modules for students for each semester. This finding may help students to improve their performance. In this research we investigate dependency between set of courses chosen by students at each level and their performance using a classification technique in order to build a performance prediction model, which is based on previous students" academic records.The finding of the study furnishes useful information to advisors in educational institution and valuable knowledge to feed analytics based systems and learning recommender systems to assist students selecting future modules to obtain optimum pathways courses.

show abstract

“…A revision of the current and future state of EDM can be seen in the review performed by Baker and Yacef (). The raw data generated by different virtual learning environments (VLEs) have been used for a wide variety of purposes, such as to predict course dropouts in massive open online courses (MOOCs; Kloft, Stiehler, Zheng, & Pinkwart, ) and also in the context of high school education (Márquez‐Vera et al ), as decision support for college admissions (Janecek & Haddawy, ), to predict if students are going to surpass a course or not (Delgado Calvo‐Flores, Gibaja Galindo, Pegalajar Jímenez, & Pérez Piñero, ), to predict the major that a student is going to pick, before the student actually enrolls in college courses (Pedro & Ocumpaugh, ), to adapt learning environments to students' cognitive styles (Guo & Zhang, ), to provide information about the performance of groups in collaborative learning environments (Perera, Kay, Koprinska, Yacef, & Zaane, ), for group formation depending on students' learning styles (Dwivedi & Bharadwaj, ), to support the recommendation elicitation process in online learning environments (Santos & Boticario, ), or to predict the score of a test before actually doing it (Feng, Heffernan, & Koedinger,(); Pardos, Gowda, Ryan, & Heffernan, ). These results have a direct impact on creating tools that can help to improve these learning experiences.…”

Section: Introductionmentioning

confidence: 99%

Improving the prediction of learning outcomes in educational platforms including higher level interaction indicators

2018

View full text Add to dashboard Cite

One of the most investigated questions in education is to know which factors or variables affect learning. The prediction of learning outcomes can be used to act on students in order to improve their learning process. Several studies have addressed the prediction of learning outcomes in intelligent tutoring systems environments with intensive use of exercises, but few of them addressed this prediction in other web‐based environments with intensive use not only of exercises but also, for example, of videos. In addition, most works on prediction of learning outcomes are based on low level indicators such as number of accesses or time spent in resources. In this paper, we approach the prediction of learning gains in an educational experience using a local instance of Khan Academy platform with an intensive use of exercises and taking into account not only low level indicators but also higher level indicators such as students' behaviours. Our proposed regression model is able to predict 68% of the learning gains variability with the use of six variables related to the learning process. We discuss these results providing explanation of the influence of each variable in the model and comparing these results with other prediction models from other works.

show abstract

Early dropout prediction using data mining: a case study with high school students

Cited by 219 publications

References 37 publications

Literature Survey on Educational Dropout Prediction

Literature Survey on Educational Dropout Prediction

Finding Most Effective Sequences of Modules for Students in Higher Education to Improve their Performance using Knowledge Discovery in Databases

Improving the prediction of learning outcomes in educational platforms including higher level interaction indicators

Contact Info

Product

Resources

About