Comparative Machine Learning Model Performance for KSI Crash Prediction

5.5 KB of comparative performance data for machine learning models predicting KSI (Killed or Seriously Injured) crashes at a safety-optimized decision threshold of 0.35. The dataset, authored by Khanh Giang Le, was last updated on April 28, 2026, and is shared under a CC-BY-4.0 license on figshare.

Use Cases

• Benchmarking machine learning models for crash severity prediction based on the comparative performance data.
• Analyzing model performance at a specific safety-optimized decision threshold (τ* = 0.35).
• Informing the selection of predictive models for road safety applications based on the reported metrics.

Strengths

• Dataset is openly licensed (CC-BY-4.0) for reuse and modification.
• File size is 5.5 KB, indicating a focused and manageable download.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely contains results from a comparative analysis of machine learning models.

Time Range

null

Freshness

Last updated 2026-04-28 17:48:52; freshness should be verified.

Geography

null