Performance Comparison of Forecasting Models for Aosta Valley Tourist Traffic

Marco Alderighi's dataset, last updated May 6, 2026, compares ensemble machine learning models for forecasting tourist flows. It is based on over 41 million vehicle passages from 14 sensor portals in Italy's Aosta Valley, integrated with meteorological and calendar data. The dataset is small at 5.5 KB and is stored in an XLS file format.

Use Cases

• Benchmarking adaptive ensemble models against static ones based on the described dynamic weighting mechanism.
• Forecasting short-term tourist traffic flows based on integrated sensor, weather, and calendar data.
• Analyzing model robustness during extreme weather events based on the described experimental validation.
• Developing resource allocation strategies for destination management based on predicted tourist flows.

Strengths

• Dataset is derived from a large-scale source of over 41 million vehicle passages.
• Experimental results show a 23.7% MAE improvement and 31.2% MSE reduction compared to individual models.
• The described ensemble framework achieved R² scores exceeding 0.94 for short-term predictions.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• The dataset file is very small (5.5 KB), suggesting it may contain only summary or model performance results, not the raw sensor data.
• Description metadata is detailed but actual data structure and content require inspection after download.

Provenance

Source

Marco Alderighi via figshare.

Collection Method

Data likely originates from 14 sensor portals monitoring vehicle passages on highways and valley roads in the Aosta Valley, Italy.

Time Range

null

Freshness

Last updated 2026-05 06 17:37:50; freshness should be verified.

Geography

Aosta Valley region, Italy.