Bertrand Ifanema Zega
Politeknik Negeri Manado

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

RANCANG BANGUNG SMART TUTOR STEM BERBASIS LEARNING ANALYTICS UNTUK MENDUKUNG SDG 4 PENDIDIKAN BERKUALITAS DI SD GMIM 23 MANADO Bertrand Ifanema Zega; Abel Enricko Dominique Sugiantho; Hendriko Mauliate Maraden Pakpahan; Christopel Hamonangan Simanjuntak; Marike Amelda Silvia Kondoj
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 2 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/bwf2c449

Abstract

The low proportion of elementary school students achieving minimum proficiency in STEM (Science, Technology, Engineering, and Mathematics) learning has become a significant challenge to achieving Sustainable Development Goal (SDG) 4 on Quality Education, particularly Indicator 4.1.1. PISA 2022 data placed Indonesia 70th out of 79 participating countries in mathematics performance, while the 2023 National Assessment showed that more than 60% of elementary school students had not achieved minimum numeracy competency. This study aims to design and develop a Smart Tutor STEM platform based on learning analytics using the K-Means Clustering algorithm to provide personalized adaptive learning experiences for students in grades 4–6 at SD GMIM 23 Manado. The method employed is Design Science Research (DSR), consisting of six stages: problem identification, definition of solution objectives, design and development, demonstration, evaluation, and communication. The platform is developed using React.js as the frontend, Python FastAPI as the backend, PostgreSQL as the database, and Scikit-learn for implementing K-Means Clustering. The K-Means algorithm groups students into three clusters based on five learning feature vectors: average STEM scores, task completion time, frequency of material repetition, answer accuracy level, and learning consistency. Clustering quality is validated using the Silhouette Score and Davies-Bouldin Index. Platform effectiveness is measured using pre-post tests with paired t-tests and N-Gain analysis, while usability is assessed using the System Usability Scale (SUS). The expected outcomes are: (1) a functional and adaptive Smart Tutor STEM platform with a Silhouette Score ≥ 0.5; (2) a significant increase in the proportion of students achieving the Minimum Mastery Criteria (KKM) in STEM (p-value < 0.05); (3) an SUS score ≥ 70 (Good category), indicating that the platform is easy to use; and (4) a tangible contribution to achieving SDG Indicator 4.1.1 at SD GMIM 23 Manado. Kata Kunci: Smart Tutor, STEM Education, Learning Analytics, K-Means Clustering, Design Science Research, SDG 4, Pendidikan Adaptif.