A Systematic Literature Review of Traffic Congestion Forecasting: From Machine Learning Techniques to Large Language Models

Traffic congestion continues to pose a significant challenge to contemporary urban transportation systems, exerting substantial effects on economic productivity, environmental sustainability, and the overall quality of life. This systematic literature review thoroughly explores the development of traffic congestion forecasting methodologies from 2014 to 2024 by analyzing 100 peer-reviewed publications according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We examine the technological advancements from traditional machine learning (achieving 75–85% accuracy) through deep learning approaches (85–92% accuracy) to recent large language model (LLM) implementations (90–95% accuracy). Our analysis indicates that LLM-based systems exhibit superior performance in managing multimodal data integration, comprehending traffic events, and predicting non-recurrent congestion scenarios. The key findings suggest that hybrid approaches, which integrate LLMs with specialized deep learning architectures, achieve the highest prediction accuracy while addressing the traditional limitations of edge case management and transfer learning capabilities. Nonetheless, challenges remain, including higher computational demands (50–100× higher than traditional methods), domain adaptation complexity, and constraints on real-time implementation. This review offers a comprehensive taxonomy of methodologies, performance benchmarks, and practical implementation guidelines, providing researchers and practitioners with a roadmap for advancing intelligent transportation systems using next-generation AI technologies.