<![CDATA[One of the key indicators for assessing the quality of higher education is the career success of its graduates. However, not all graduates succeed in securing employment in fields relevant to their area of study. This study aims to analyze the influence of academic and non-academic factors on career alignment and to develop a predictive model using machine learning algorithms. The data used in this study were obtained from an alumni tracer study and student academic records at Universitas Muria Kudus (UMK), comprising a total of 311 records after data transformation. The predictor variables include Grade Point Average (GPA), length of study, teamwork skills, and scholarship participation, with a single target variable representing career alignment. Three classification algorithms were applied: Decision Tree, Random Forest, and Support Vector Machine (SVM). The results show that teamwork skills and scholarship participation have a moderate positive correlation with career alignment, while length of study has a negative correlation, and GPA has a very weak positive correlation. Random Forest demonstrated the best performance with an AUC score of 0.86 and a Cohen’s Kappa score of 0.62, indicating good and stable classification quality. The findings from the variable analysis and classification model can be utilized in developing a career alignment prediction system and as a basis for decision-making in strategies to improve graduate quality in line with labor market needs.]]>
Copyrights © 2025
