Skip to main content

Table 6 Data Selection

From: Predicting academic success in higher education: literature review and best practices

MethodsWhen to useAdvantagesDisadvantages
Vertical selectionTo remove redundant or irrelevant featuresFacilitate understanding of the extracted pattern and rises the speed of the learning stageRequires a good understanding of the data domain
Horizontal selectionTo remove redundant and/or conflicting instancesEnhance the quality of input data, thus enable improved performance of DM modelsIn descriptive analysis, it is best to have as many instances as possible.