Road traffic accident severity prediction using causal inference and machine learning
Bibliographic record
Abstract
The global rise in road traffic accidents presents substantial challenges across economic, societal, and public health domains, leading to millions of injuries and fatalities annually. Current studies on modeling and analyzing traffic accident frequency largely treat the issue as a classification task, primarily utilizing learning-based or ensemble methods. However, these approaches frequently neglect the intricate relationships among the multifaceted factors—such as road complexity, environmental conditions, driver behavior, and contextual elements—that contribute to traffic accidents and hazardous scenarios. We propose an approach that employs causal inference and causal Machine Learning (ML) techniques to predict accident severity and identify key causal factors. We evaluate our proposed approach with two datasets, from Ethiopia and UK. Given the inherent imbalance in these datasets, the Synthetic Minority Oversampling Technique (SMOTE) is utilized to achieve balanced data representation. Uplift modeling and causal inference methods are employed for severity prediction. Individual Treatment Effect (ITE) and Average Treatment Effect (ATE) are used to make interpretations of the predictions. Our research contributes to understanding and mitigating the impact of road traffic accidents through advanced causal analysis techniques, offering actionable insights for policymakers, urban planners, and public health officials globally.
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 | 0.005 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".