Using Genetic Algorithms for Data Mining Optimization in an Educational Web-Based System

Abstract

Abstract. This paper presents an approach for classifying students in order to predict their final grade based on features extracted from logged data in an education web-based system. A combination of multiple classifiers leads to a significant improvement in classification performance. Through weighting the feature vectors using a Genetic Algorithm we can optimize the prediction accuracy and get a marked improvement over raw classification. It further shows that when the number of features is few; feature weighting is works better than just feature selection.

Data mining in course management systems: Moodle case study and tutorial

“…This is supervised classification which provides a collection of labeled (preclassified) patterns, the problem being to label a newly encountered, still unlabeled, pattern. In e-learning, classification has been used for: discovering potential student groups with similar characteristics and reactions to a specific pedagogical strategy (Chen, Liu, Ou, & Liu, 2000); predicting students' performance and their final grade (Minaei-Bidgoli & Punch, 2003); detecting students' misuse or students playing around (Baker, Corbett, & Koedinger, 2004); predicting the students' performance as well as to assess the relevance of the attributes involved (Kotsiantis, Pierrakeas, & Pintelas, 2004); grouping students as hint-driven or failure-driven and finding students' common misconceptions (Yudelson, Medvedeva, Legowski, Castine, & Jukic, 2006); identifying learners with little motivation and finding remedial actions in order to lower drop-out rates (Cocea & Weibelzahl, 2006); for predicting course success (Hamalainen & Vinni, 2006).…”

A Scalable Heuristic Classifier for Huge Datasets: A Theoretical Approach

“…It means 29 misclassifications have totally occurred in recognition of these two digits (classes). The mostly erroneous pair-classes are respectively (2, 3), (0, 5), (3,4), (1,4), (6,9) and so on according to this matrix. Assume that the ith mostly EPPC is denoted by EPPC i .…”

“…In such situations, employing ensemble of classifying learners instead of single classifier can lead to a better learning [6]. Although obtaining the more accurate classifier is often targeted, there is an alternative way to obtain it.…”

“…In General, it is ever-true sentence that "combining the diverse classifiers which are better than random results in a better classification performance" [2], [6] and [10]. Diversity is always considered as a very important concept in classifier ensemble methodology.…”

Ensembles of partitions via data resampling

“…A measure of consistency between two clusters is defined in [8]. Data resampling has been used as a tool for estimating the validity of clustering [9], [10] and its reliability [11], [12].…”