engleski

CRISP-DM process model in educational setting

Data mining techniques are being used in areas of prediction and classification, replacing traditional statistical approaches. Their application spans a wide variety of fields and education is one of them. This paper carries out a comprehensive methodology based on the CRISP DM process for data mining in order to gain insights into academic performance prediction. Paper explores to what extent socio-demographic variables, previous education, motivation and learning style can help in identifying successful students. Based on the decision tree method, profile of the typical successful information technology student is identified. Based on the research results it can be concluded that the academic performance is significantly influenced by previous education.

academic success, data mining, decision tree, process model

nije evidentirano