Rail Freight Volume Predictions Using Fuzzy Granules and SVM, 2013-2022

Lanzhou Freight Center in China provided 114 monthly observations of rail freight volume from 2013 to 2022. The dataset contains results from a prediction model that uses Fuzzy Information Granulation and an Improved Particle Swarm Optimization-Support Vector Machine (IPSO-SVM) algorithm. Author Yunbo Gao published the data on figshare under a CC-BY-4.0 license.

Use Cases

• Benchmarking granular time-series prediction models based on the described FIG-IPSO-SVM methodology.
• Analyzing uncertainty in freight volume forecasts based on the tri-granular (Low, R, Up) representations.
• Studying the application of evolutionary optimization (IPSO) for hyperparameter tuning in SVM models for small-sample predictions.

Strengths

• Contains results validated against 9 years of operational records (2013–2022).
• The proposed model achieved a specific mean maxima of absolute percentage error of 5.03% and a prediction interval relative width of 8.53%.
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope, likely containing only model results or summary statistics.

Provenance

Source

Yunbo Gao

Collection Method

Model results from a proposed FIG-IPSO-SVM framework applied to operational records.

Time Range

2013 to 2022

Freshness

Last updated 2026-05 17:39:44; freshness should be verified.

Geography

Lanzhou Freight Center, China