← Back to all models

AVM model details: Switzerland

Performance metrics for AVMs in this location.

Model type

Select the type of valuation model you want to view.

List price estimation model

Estimates list prices in this location from historical data and market trends.

Key performance metrics

Median Absolute Percentage Error (M. MAPE)22.0%Half of our predictions are within this percentage of the actual value
Testing R² Score0.490How much of the price variation our model explains
Root Mean Square ErrorCHF 561,215Average prediction error in the local currency
Mean Absolute ErrorCHF 355,900Average absolute difference between predicted and actual

Accuracy distribution

Percentage of predictions within various error ranges

Within 5%12.6%
Within 10%27.0%
Within 15%37.8%
Within 20%47.3%

Prediction bias analysis

Does the model tend to overestimate or underestimate?

Mean Bias-CHF 70,651Average prediction bias (+ means overestimate)
Median Bias+CHF 9,368Typical prediction bias
Over-prediction Rate51.3%Percentage of predictions that are above the actual value
Under-prediction Rate48.7%Percentage of predictions that are below actual value

Error distribution percentiles

The absolute error amount at different percentiles - for example, '90th percentile: CHF 50,000' means 90% of predictions have errors less than CHF 50,000

Percentile10th25th50th75th90th95th
Error AmountCHF 44,036CHF 101,287CHF 230,034CHF 446,004CHF 768,215CHF 1,149,042

Model configuration & training

Training Samples2207
Testing Samples1234
Training R²0.630
Testing R²0.490
Last Updated2026-11-11

Additional performance metrics

Mean Absolute Percentage Error30.3%Average percentage error across all predictions
Forecast Standard DeviationCHF 556,750Spread of prediction errors
Coefficient of Variation45.8%Relative variability of predictions
10th Percentile Error %4.0%10% of predictions have error less than this
90th Percentile Error %59.9%90% of predictions have error less than this