Abstract
Data Mining is a growing field, a strand of which is Educational data mining (EDM). EDM is currently used to help institutions and students through creating accurate predictions that are considered in decision making. One of EDM’s concerns is that of predicting students’ academic performance and fundamental learning difficulties in a particular course. In fact, EDM can help computer science (CS)-enrolled students to predict whether they can pass their courses without taking further action. An introductory programming course is usually the first challenging course faced by students in CS departments since a student’s performance in such a course is highly based on their intellectual skills. This paper presents a real case study from one of Saudi Arabia’s leading universities. This study used well-known prediction models— specifically, decision tree (DT), k-nearest neighbor (kNN), Naïve Bayes (NB), and support vector machine (SVM) models—to create a reliable prediction model for at-risk students in an introductory programming course using preliminary performance information showing their self-efficacy. The results of this study showed that the DT and SVM models yielded the best performance with the highest accuracy rate (99.18%). Furthermore, comparisons between the applied models were conducted with different evaluation metrics.
Highlights
Data mining (DM) principles and techniques can be useful in different arenas, such as medicine, marketing, customer services, web mining, engineering, and education
Several algorithms have been used in classification tasks to predict student performance, including decision tree (DT), Bayesian classifier, artificial neural network (ANN), support vector machine (SVM), and k-nearest neighbor (kNN) algorithms
The experiments of this study showed that both the C4.5 DT and classification and regression tree (CART) classifiers yielded accuracies greater than 98% and the M5 model regression tree performed well in both cross-validation and supplied test-set situations to predict the numerical data of major tests
Summary
Data mining (DM) principles and techniques can be useful in different arenas, such as medicine, marketing, customer services, web mining, engineering, and education. DM is a tool that helps institutes to identify and extract significant, hidden information from their organizational databases [1]. This is done through an analytical approach by analyzing the data to find a pattern using a DM technique, such as association, classification, or clustering [2]. Research interest in EDM has grown rapidly, as it can be used to evaluate learning effectiveness, improve teaching performance, and organize institutional resources, among many other applications [1], [7]. Classification is a learning technique that involves creating a model called a classifier, which is able to assign class labels to unidentified data. Several algorithms have been used in classification tasks to predict student performance, including DT, Bayesian classifier, artificial neural network (ANN), SVM, and kNN algorithms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
