Machine Learning-Based Teacher Education Student Placement Model Via Interest Profile and Diagnostic Test

Traditional student placement in college programs based on academic performance, interviews, and student choice may not always yield optimal results. This study proposes a machine learning-based model for teacher education program placement, integrating student interests and diagnostic test results across various specializations. Data from 208 freshmen in a teacher education institution (AY 2024-2025) were collected using a validated interest profile questionnaire and diagnostic test. Various machine learning methods were evaluated for classification performance. Results showed that most students exhibited strong interest in their chosen specialization, highlighting interest as a key placement factor. Diagnostic test performance trends further indicated that students tend to excel in their respective fields. The final placement model employed artificial neural networks, support vector machines, gradient boosting, and adaptive boosting, each achieving at least 80% classification accuracy and F1 score. This model offers a systematic and data-driven approach to optimizing teacher education student placement.