Application Of Data Mining Techniques For Student Success And Failure Prediction (The Case Of Debre_Markos University)

摘要: This research work has investigated the potential applicability of data mining technology to predict student success and failure cases on University students' datasets. CRISP-DM (Cross Industry Standard Process for Data mining) is a methodology be used by research. Classification prediction functionalities are extract hidden patterns from data. These can seen in relation different variables records. The classification rule generation process based decision tree Bayes as technique generated rules were studied evaluated. collected MS_EXCEL files, it been preprocessed model building. Models built tested using sample dataset 11,873 regular undergraduate students. Analysis done WEKA 3.7 application software. results offer helpful constructive recommendations academic planners universities learning enhance their making process. will also aid curriculum structure modification order improve performance. Students able decide about field study before they enrolled specific previous experience taken research- findings. findings indicated that EHEECE (Ethiopian Higher Education Entrance Certificate Examination) result, Sex, Number students class, number courses given semester, major factors affecting performances. So, bases level increase possible prevent educational institutions serious financial strains.