Predicting Secondary School Students' Performance Utilizing a Semi-supervised Learning Approach

Abstract

Educational data mining constitutes a recent research field which gained popularity over the last decade because of its ability to monitor students' academic performance and predict future progression. Numerous machine learning techniques and especially supervised learning algorithms have been applied to develop accurate models to predict student's characteristics which induce their behavior and performance. In this work, we examine and evaluate the effectiveness of two wrapper methods for semisupervised learning algorithms for predicting the students' performance in the final examinations. Our preliminary numerical experiments indicate that the advantage of semisupervised methods is that the classification accuracy can be significantly improved by utilizing a few labeled and many unlabeled data for developing reliable prediction models.

An Auto-Adjustable Semi-Supervised Self-Training Algorithm

“…Subsequently, in each Tri-training round, if two classifiers agree on the labeling of an unlabeled instance while the third one disagrees, then these two classifiers will label this instance for the third classifier. It is worth noticing that the "majority teach minority strategy" serves as an implicit confidence measurement which avoids the use of complicated time-consuming approaches for explicitly measuring the predictive confidence, and hence the training process is efficient [4].…”

“…Hence, these methods have the advantage of reducing the effort of supervision to a minimum, while still preserving competitive recognition performance. Nowadays, these algorithms have great interest both in theory and in practice and have become a topic of significant research as an alternative to traditional methods of machine learning, since they require less human effort and frequently present higher accuracy [4][5][6][7][8][9][10]. The main issue of semi-supervised learning is how to efficiently exploit the hidden information in the unlabeled data.…”

“…Self-training constitutes perhaps the most popular and frequently used SSL algorithm due to its simplicity and classification accuracy [4,5,9]. This algorithm wraps around a base learner and uses its own predictions to assign labels to unlabeled data.…”

On Ensemble SSL Algorithms for Credit Scoring Problem

“…Then, iteratively each base learner teaches the other with its most confidently predicted unlabeled examples, hence augmenting their training sets. However, in most real-case scenarios this assumption is a luxury hardly met [21].…”

“…To this end, they are generally considered as the appropriate machine learning methodology to build powerful classifiers by extracting information from both labeled and unlabeled data [16]. Self-labeled algorithms constitute the most popular and frequently used class of SSL algorithms, thus have been efficiently applied in several real-world problems [17][18][19][20][21][22][23][24]. These algorithms wrap around a supervised prediction base learner and exploit the unlabeled data via a self-learning philosophy.…”