AMGST: Statistical and Significance Analysis for Traffic Forecasting

5.5 KB of statistical analysis results for the AMGST traffic forecasting model. The dataset, authored by Pei Shi and last updated in June 2026, contains experimental results from evaluating the model on four public traffic datasets. It is hosted on figshare under a CC-BY-4.0 license.

Use Cases

• Benchmarking new traffic forecasting models against the reported AMGST results.
• Analyzing the significance of model improvements using the provided statistical tests.
• Studying the performance of adaptive multi-graph convolution on different traffic datasets (speed and flow).

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• Results are derived from experiments on four distinct public traffic datasets, as mentioned in the description.
• Has a clear, permissive license (CC-BY-4.0).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The 5.5 KB size suggests the dataset contains summary results, not the underlying raw traffic data.

Provenance

Source

figshare

Collection Method

Likely contains statistical results from model experiments, as described in the associated research.

Freshness

Last updated 2026-06-04 17:36:37; freshness should be verified.