Predictive Analytics for Vehicle Utilization and Fleet Decision Support in Higher Education

View at publisher Summarise with VIRAT
Authors: Sharifah Masyitah Binti Syed Mohamad, Norulhidayah Binti Isa, Syahrul Hezrin Mahmud
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Efficient vehicle utilization is vital for higher education institutions (HEIs) that rely on transportation for academic, administrative, and operational needs. Traditional manual fleet management methods often poor resource allocation and limited visibility. This study analyzes vehicle utilization and travel patterns in a HEI to support datadriven fleet management. Predictive analytics techniques were applied to historical vehicle logbook data (2023–2024) using machine learning models, including Random Forest, Decision Tree, and Support Vector Machine. Two experiments were conducted; classification of vehicles based on utilization trends and prediction of daily trip counts. Results demonstrated that Random Forest achieved the best performance, with an accuracy of 77.86% in the classification task and a root mean square error (RMSE) of 0.773 in the regression task. An interactive dashboard was developed using Power BI to visualize vehicle mileage, driver activity, and underutilized resources. The findings highlight the potential of integrating predictive analytics and dashboard visualization to improve fleet planning, optimize resource allocation, and enhance operational efficiency in higher education environments. Future work may include real-time tracking, automated data collection, and predictive fuel monitoring.

Fields of Study & Subjects

Big Data and Business Intelligence Data Mining and Machine Learning Applications Online Learning and Analytics

Publication details

Journal / source
International Conference on Cognitive Systems and Computer Interaction (ICoSCI)
Pages
1–6
Publication date
15 January 2026
Language
EN