Cross-Location Machine Learning Model Generalization Results

A 9.5 KB Excel file containing cross-location generalization results for machine learning models. The data includes mean and standard deviation values for R-squared and Mean Absolute Error metrics when models are trained on one location and evaluated on three others. It was authored by Usman Ali and last updated on April 30, 2026.

Use Cases

• Evaluating model generalization across different geographic locations based on the cross-location testing results.
• Comparing the performance of different ML models using R-squared and MAE metrics from the described evaluation.
• Analyzing the variance in model performance (S.D.) when applied to unseen locations.

Strengths

• Dataset is small (9.5 KB), facilitating quick download and inspection.
• Provides specific performance metrics (R² and MAE) with reported standard deviations.
• Released under a permissive CC-BY-4.0 license for open use.

Limitations

• Row count and specific column definitions are unknown, requiring manual inspection after download.
• The description is minimal; the exact nature of the models, locations, and target variable is not detailed.
• The geographic and temporal context of the source data is unspecified, which may limit interpretation.

Provenance

Source

figshare, authored by Usman Ali.

Collection Method

Likely contains aggregated results from machine learning experiments evaluating cross-location performance.

Freshness

Last updated 2026-04-30 17:54:57; freshness should be verified.

Geography

Implies multiple locations, but specific geography is null.