A comprehensive review of traffic prediction: From traditional machine learning to AutoML
Bibliographic record
Abstract
In the rapidly urbanizing world, efficient traffic prediction is essential for reducing congestion, optimizing travel times, and enhancing road safety. Traditional machine learning (ML) models have long been used for traffic forecasting but often struggle with unstructured data and capturing the complex temporal and spatio-temporal relationships inherent in traffic networks. Deep learning (DL) models, by contrast, can effectively handle large datasets and learn complex patterns, yet they still demand substantial human expertise for architecture design, hyperparameter tuning, and dataset-specific adaptation. This paper presents a comprehensive review of the evolution of traffic prediction models, highlighting the limitations of ML and DL approaches and introducing Automated Machine Learning (AutoML) as a promising solution. We discuss how AutoML can automate key stages of the ML pipeline—including data preprocessing, feature engineering, model learning, and model updating—reducing the need for human expertise, improving generalizability, and enabling model adaptation across datasets. While some studies have integrated AutoML components into traffic prediction tasks, a fully automated, end-to-end pipeline remains an open research challenge. This review identifies current gaps, explores AutoML’s potential to address these challenges, and outlines future directions for advancing traffic prediction through AutoML.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".