Predicting Public Personnel Selection Examination Achievement: A Data Mining Approach

This research investigates the predictive variables related to the Public Personnel Selection Examination (KPSS), utilized for recruitment in public institutions and organizations. The study explores predictor variables' importance levels by analysing longitudinal data, including examinees' high-stakes exams, demographic information, and educational backgrounds. It compares the prediction performances of machine learning algorithms such as artificial neural networks, random forest, support vector machine, and k-nearest neighbour. The findings reveal that the quantitative test of the graduate education exam is the most influential predictor, closely followed by the mathematics test of the university entrance exam. These results highlight the importance of quantitative reasoning skills in predicting KPSS achievement. Additionally, variables related to undergraduate programs and universities demonstrate significant importance in predicting KPSS achievement. Notably, the artificial neural networks model demonstrates superior predictive accuracy compared to other models, indicating its effectiveness in KPSS prediction. This research sheds light on important predictors of KPSS achievement and provides valuable insights into the effectiveness of different prediction models.