Mobility Trend Forecast Accuracy Comparison Across Location Categories

Aritath Siraphatwongkorn published this dataset in March 2026, comparing the forecast accuracy of mobility trends using ARIMA, FB-PROPHET, and Feature Engineered XGBoost models. The dataset is a 9.5 KB Excel file containing results across different location categories.

Use Cases

• Compare ARIMA, FB-PROPHET, and XGBoost forecast accuracy metrics for mobility trends across location categories.
• Analyze model performance variations by location category to identify context-dependent forecasting strengths.
• Use the provided accuracy results to benchmark new forecasting models against established ARIMA, FB-PROPHET, and XGBoost approaches.

Strengths

• Directly compares three distinct forecasting methodologies: ARIMA, FB-PROPHET, and Feature Engineered XGBoost.
• Results are segmented across location categories, enabling granular analysis.
• Published under a permissive CC BY 4.0 license for reuse.

Limitations

• The dataset is very small at 9.5 KB, indicating limited scope and likely a summary of results rather than raw time series data.
• Column names and sample data are unavailable, obscuring the specific accuracy metrics and data structure.
• The input provides no information on the underlying mobility data's temporal coverage, geography, or sample size.

Provenance

Source

figshare

Collection Method

Results from forecasting experiments comparing ARIMA, FB-PROPHET, and Feature Engineered XGBoost models.

Time Range

null

Freshness

Last updated March 2026.

Geography

null