Use of Decision Tree and Fuzzy Logic Methods to Predict Academic Achievement of University Freshmen

SALAHLI M. A., Gasimzade T., Salahli V., Alasgarova F., Guliyev A.

11th International Conference on Theory and Applications Soft Computing, Computing with Words and Perceptions and Artificial Intelligence, ICSCCW 2021, Antalya, Turkey, 23 - 24 August 2021, vol.362 LNNS, pp.156-164 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 362 LNNS
  • Doi Number: 10.1007/978-3-030-92127-9_24
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.156-164
  • Keywords: Academic achievement, Decision tree, Fuzzy inference, Predictive model
  • Çanakkale Onsekiz Mart University Affiliated: Yes


© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.It is not easy for students who have just entered the university to adapt to the new education and living environment. In this process, social-economic, educational, and personal factors have a great impact on the academic achievements of first-year students. In this study, the aim is to determine the factors affecting the academic success of university freshmen and to predict the academic success of students by using decision tree and fuzzy logic methods together, considering the most important factors. Students’ achievement was predicted by the decision tree method considering the students’ university entrance scores, satisfaction with the educational environment, accommodation, attendance to the course, and preference of the department as input of the prediction model. Fuzzy inference rules were created based on the decision tree obtained from implementation of the J48 method, which provides a better understanding of the dependence between students’ academic achievement and impact factors.