A Career Track Recommender System for Senior High School Students using Fuzzy Log

Rule-based algorithms are mostly used in recommender systems but still, cannot address the issue of uncertainty in decision making particularly to senior high school students in choosing the right career track because of numerous influential factors that may affect their decisions. That is why a career track recommender system using fuzzy logic has been developed to address this issue. In this paper, the significant factors that is most influential to the decision of the students as best attributes were determined using feature selection filtering techniques and used as crisp inputs. The result shows that the developed fuzzy model performs a high predictive accuracy based on the computed mean absolute error (MAE) and root-mean-square error (RMSE) scores which decreases from the training, to the validation and test sets. The recommendation returns the best possible result based on the computed normalized discounted cumulative gain (nDCG) which is 0.948 from the desired to the actual preference of students which is almost near to 1.0. With these, the developed recommender system is highly recommended as perceived by the users in terms of usability, maintainability and portability.