Oversampling Methods Comparison for Traffic Accident Severity in Kent, UK (2022-2024)

5.5 KB of test set data from a study comparing oversampling methods for analyzing traffic accident severity. The dataset, created by Huashan Ye and last updated in April 2026, supports research into spatial disparities in crash outcomes between urban and rural areas of Kent, UK, from 2022 to 2024.

Use Cases

• Comparing oversampling method performance for predicting accident severity based on the described test set.
• Analyzing urban-rural heterogeneity in crash risk factors as mentioned in the study description.
• Interpreting model predictions for traffic safety using SHAP values, as referenced in the study framework.
• Developing context-sensitive risk mitigation policies based on the identified behavioral and infrastructure-driven risk profiles.

Strengths

• Data is associated with a study explicitly linked to UN Sustainable Development Goals (SDG 3 and SDG 11).
• The underlying study uses a spatially segmented machine learning framework and SHAP explanations for model interpretability.
• Dataset has a clear temporal coverage from 2022 to 2024 for Kent, UK.

Limitations

• Dataset is very small at 5.5 KB, indicating limited scope.
• Row count and column-level documentation are unknown, which limits suitability assessment.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

figshare, author Huashan Ye.

Collection Method

Likely derived from disaggregated accident data as part of a research study comparing oversampling methods.

Time Range

2022–2024

Freshness

Last updated 2026-04-24 17:52:24; freshness should be verified.

Geography

Kent, United Kingdom