Eisyaniah Desvazulinda
Batam University, Indonesia

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

Found 1 Documents
Search

Prediction Model of Batam University Management Information System Based on Regression and Machine Learning Fendi Hidayat; Eisyaniah Desvazulinda; Syakinah Warrahmah
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 9 No. 1 (2026): Jurnal Teknologi dan Open Source, June 2026
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v9i1.5648

Abstract

The implementation of Management Information Systems (MIS) in higher education is strongly influenced by the use of information technology (IT) and the digital competence of its users. This study aims to analyze the influence of IT use and digital competence on MIS at Batam University, as well as to develop the best prediction model by comparing conventional statistical methods and machine learning algorithms. Research data were collected through a Likert-scale-based questionnaire from respondents selected using a purposive sampling technique. Data analysis was performed using a combination of Multiple Linear Regression, Random Forest Regressor, and Gradient Boosting Regressor. The results of statistical tests indicate that the use of IT and digital competence simultaneously have a positive and significant effect on MIS with a coefficient of determination ($R^2$) of 87.40%. On the other hand, the results of the machine learning model evaluation show that Random Forest Regressor provides the best performance with the lowest MAE and RMSE values, and the highest prediction accuracy ($R^2$ Score) reaching 0.905072. This study concludes that the integration of statistical and machine learning approaches can produce an accurate and adaptive MIS prediction model to support data-driven decision making at Batam University