Research Article
Student Academic Performance Prediction Model Based on Machine Learning in PTIK Unimed
@INPROCEEDINGS{10.4108/eai.16-9-2025.2361084, author={Tansa Trisna Astono Putri and Reni Rahmadani and Rosma Siregar and Hanapi Hasan and Aida Khairina and Afif Hamzah}, title={ Student Academic Performance Prediction Model Based on Machine Learning in PTIK Unimed}, proceedings={Proceedings of the 7th International Conference on Innovation in Education, Science, and Culture, ICIESC 2025, 16 September 2025, Medan, Indonesia}, publisher={EAI}, proceedings_a={ICIESC}, year={2026}, month={3}, keywords={machine learning academic performance prediction student performance ptik unimed higher education data mining}, doi={10.4108/eai.16-9-2025.2361084} }- Tansa Trisna Astono Putri
Reni Rahmadani
Rosma Siregar
Hanapi Hasan
Aida Khairina
Afif Hamzah
Year: 2026
Student Academic Performance Prediction Model Based on Machine Learning in PTIK Unimed
ICIESC
EAI
DOI: 10.4108/eai.16-9-2025.2361084
Abstract
This research aims to analyze the implementation of machine learning algorithms in predicting the academic performance of students in the PTIK Study Program at Universitas Negeri Medan. The study utilizes a machine learning model including Naive Bayes, to process academic and demographic data of students. The methodology involves data preprocessing, feature selection, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results indicate that machine learning algorithms can effectively predict student academic performance, with the Random Forest model achieving the highest accuracy among the tested algorithms. The findings highlight the potential of machine learning-based prediction models to support early identification of students at risk and inform strategic interventions to improve academic achievement. This research contributes to the development of data-driven decision-making processes in higher education, particularly in the context of the PTIK Study Program at Unimed.
