Machine Learning Model for Human Resource Placement in Higher Education

Abstract

This study presents the development and evaluation of a machine learning model designed to support human resource (HR) placement decisions in higher education institutions. Using combined personnel data from STMIK YMI Tegal and Politeknik Harber, we built a predictive model to estimate staff attendance at institutional progress reporting events, a critical indicator for performance evaluation and role suitability. The dataset comprised 137 records with six categorical predictors: Position, Homebase, Origin, Tegal_Status, Gender, and Institution. Categorical variables were encoded using label encoding, and a Random Forest classifier was trained using a stratified 75%/25% train-test split. The model achieved a held-out test accuracy of 97.14%, precision of 93.33%, recall of 100%, and F1-score of 96.55%, outperforming baseline models (Logistic Regression and Decision Tree). Five-fold cross validation confirmed robust generalization with an average accuracy of 91.22%. Feature importance analysis revealed Position as the most influential variable (76.88% importance), followed by Homebase and Origin. The results suggest that machine learning, particularly ensemble based methods, can provide reliable decision support tools for HR managers in academic settings, enabling data driven placement strategies. This research highlights the potential of predictive analytics for optimizing staff assignments and fostering institutional effectiveness. Future work should include larger datasets, additional features, and external validation to enhance model generalizability.