A Systematic Review of AI and Machine Learning Applications in Predictive Risk Management for Public Transport Safety: Pathways to Fintech Integration
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
This systematic review examines AI and machine learning (ML) applications in predictive risk management for public transport safety and proposes pathways for fintech integration. Theoretically underpinned by Socio-Technical Systems (STS) and Adaptive Governance, the research synthesizes 78 peer-reviewed articles using the PRISMA 2020 protocol. Findings report on a mature body of research that is led by supervised and deep learning algorithms for accident prediction but with car-road emphasis and a glaring lack of alignment with financial systems. The paper contributes by proposing the Fintech-Transport Safety Integration Framework (FTSIF) which theorizes three complementary paths: data-driven insurance models, smart safety contracts, and forward-looking investment tools. Theoretically, the FTSIF extends STS by formally incorporating financial subsystems. In practice, it provides a template for cross-sector collaboration to build resilient safety systems. Socially, the system guarantees more balanced resource distribution but needs to be robustly governed to prevent algorithmic discrimination. The study concludes that only such an integrative solution can assist in moving towards proactive, cost-effective risk prevention from reactive safety, offering a worthy contribution to the argument on next-generation mobility for cities. The framework awaits empirical validation in diverse transport contexts.
Fields of Study & Subjects
Traffic and Road Safety
IoT and GPS-based Vehicle Safety Systems
Evaluation and Optimization Models
Publication details
- Journal / source
- Dibon Journal of Business
- Volume
- 2
- Issue
- 1
- Pages
- 340–362
- Publication date
- 1 April 2026
- Language
- EN