« Back to Volume 11 (2002), Issue 4
Pojdi na slovensko stran članka / Go to the article page in Slovene
Comparison of tree types of models for the prediction of final academic achievement
Silvana Gasar, Marko Bohanec & Vladislav Rajkovič
Full text (pdf) | Views: 13 | Written in Slovene. | Published: December 23, 2002
Abstract: For efficient prevention of inappropriate secondary school choices and by that academic failure, school counselors need a tool for the prediction of individual pupil's final academic achievements. Using data mining techniques on pupils' data base and expert modeling, we developed several models for the prediction of final academic achievement in an individual high school educational program. For data mining, we used statistical analyses, clustering and two machine learning methods: developing classification decision trees and hierarchical decision models. Using an expert system shell DEX, an expert system, based on a hierarchical multi-attribute decision model, was developed manually. All the models were validated and evaluated from the viewpoint of their applicability. The predictive accuracy of DEX models and decision trees was equal and very satisfying, as it reached the predictive accuracy of an experienced counselor. With respect on the efficiency and difficulties in developing models, and relatively rapid changing of our education system, we propose that decision trees are used in further development of predictive models.
Keywords: academic achievement, prediction, occupational guidance, decision making, expert systems, models, data mining
