IMPLEMENTING DATA MINING TOOL FOR STUDENTS' ACADEMIC PERFORMANCE PREDICTION

Abstract

 This work describes the development of EmfactorPredictz, a tool developed for students' academic performance prediction. The tool applies a Data Mining model which comprises six algorithms (K-Nearest Neighbor, Naive Bayes, Decision Tree, Support Vector Machine, Linear Discriminant Analysis and Logistic regression) and taking into consideration the various factors that can affect students' academic performance, the tool is able to predict either the student is going to pass or fail with a degree of accuracy. Results gotten from this research showed that you can actually predict the performance of a student provided you can get the results he/she obtained from past evaluations. The research also revealed that other factors apart from grades can also affect the performance of students.