Predictive analytics applications in smart bus system: a systematic literature review of challenges and opportunities in Malaysia
Buses play a crucial role in sustainable urban mobility in Malaysia, serving millions of commuters daily. However, persistent issues such as unreliable service information, inconsistent schedules, late arrivals, and inefficient route planning have contributed to declining user trust and passenger sa...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Malque Publishing
2026
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/47278/1/e2026451.pdf https://malque.pub/ojs/index.php/mr/article/view/14360/6050 https://umpir.ump.edu.my/id/eprint/47278/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Buses play a crucial role in sustainable urban mobility in Malaysia, serving millions of commuters daily. However, persistent issues such as unreliable service information, inconsistent schedules, late arrivals, and inefficient route planning have contributed to declining user trust and passenger satisfaction. Addressing these challenges increasingly requires integrating predictive analytics and Internet of Things (IoT) technologies to enable data-driven decision-making for more reliable and efficient bus services. The purpose of this study is to systematically review predictive analytics applications for smart bus systems in Malaysia, with a focus on identifying key challenges, research gaps, and opportunities for improving public transport performance. This study begins by outlining the key challenges faced by the Malaysian public transport system, including service reliability issues, data fragmentation, and limited adoption of advanced analytics. In the methodology section, a systematic literature review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. Structured searches were conducted across major academic databases, including Scopus and IEEE Xplore, yielding 28 relevant articles selected according to predefined inclusion and exclusion criteria. The study selection process was documented using a PRISMA flow diagram to ensure transparency and reproducibility. The results and discussion highlight opportunities for Malaysia to further leverage predictive analytics to enhance smart bus systems. The review findings indicate that machine learning and deep learning models are increasingly applied to bus arrival time prediction, demand forecasting, and route optimization. However, most existing studies remain limited in scope and often lack comprehensive integration with real-time Internet of Things (IoT) data. Common challenges identified include fragmented data sources, limited technical capacity, and insufficient alignment between technological initiatives and public transport policies. In conclusion, this review underscores the need for important integration between predictive analytics and IoT infrastructure within Malaysian smart bus systems. |
|---|