A Systematic Literature Review on Data Mining Techniques for Smart Transportation: Trends, Challenges, and Future Prospects

This article presents a Systematic Literature Review (SLR) on the use of data mining techniques in intelligent transportation systems (ITS). The review follows PRISMA procedures encompassing identification, screening, feasibility evaluation, inclusion, and data synthesis. Articles were retrieved using Publish or Perish with Scopus as the primary database, and data were coded and classified using Microsoft Excel. From 4,059 publications initially identified, 36 highly relevant papers were selected and analyzed across thematic areas such as demand forecasting, accident prevention, efficiency optimization, and intelligent transport integration. The novelty of this study lies in its comprehensive synthesis and mapping of methodological patterns, data sources, and evaluation practices in ITS-related research providing an integrated perspective that has not been consolidated in prior reviews. The findings reveal that urban traffic management decisions supported by data mining particularly clustering, classification, and predictive analysis techniques can significantly enhance system responsiveness and safety. However, several challenges persist, including the limited integration between predictive models and transportation policy frameworks, inconsistent data quality, and interoperability issues. Data mining also presents opportunities to improve public transport safety and address mobility challenges in developing countries. To maximize the impact of data mining on adaptive and sustainable transport systems, future research should focus on enhancing real-time analytics, developing inclusive and policy-aware frameworks, and promoting cross-regional implementation to ensure broader applicability and long-term impact in intelligent mobility systems.