Performance metrics for AVMs in this location.
Select the type of valuation model you want to view.
Estimates list prices in this location from historical data and market trends.
| Median Absolute Percentage Error (M. MAPE) | 9.3% | Half of our predictions are within this percentage of the actual value |
| Testing R² Score | 0.960 | How much of the price variation our model explains |
| Root Mean Square Error | $52,463 | Average prediction error in the local currency |
| Mean Absolute Error | $27,986 | Average absolute difference between predicted and actual |
Percentage of predictions within various error ranges
| Within 5% | 29.9% |
| Within 10% | 52.9% |
| Within 15% | 69.4% |
| Within 20% | 78.2% |
Does the model tend to overestimate or underestimate?
| Mean Bias | -$6,760 | Average prediction bias (+ means overestimate) |
| Median Bias | -$709 | Typical prediction bias |
| Over-prediction Rate | 46.9% | Percentage of predictions that are above the actual value |
| Under-prediction Rate | 53.1% | Percentage of predictions that are below actual value |
The absolute error amount at different percentiles - for example, '90th percentile: $50,000' means 90% of predictions have errors less than $50,000
| Percentile | 10th | 25th | 50th | 75th | 90th | 95th |
|---|---|---|---|---|---|---|
| Error Amount | $1,221 | $3,566 | $12,351 | $33,902 | $69,445 | $104,880 |
| Training Samples | 22000 |
| Testing Samples | 3132 |
| Training R² | 0.990 |
| Testing R² | 0.960 |
| Last Updated | 2026-10-12 |
| Mean Absolute Percentage Error | 17.1% | Average percentage error across all predictions |
| Forecast Standard Deviation | $52,026 | Spread of prediction errors |
| Coefficient of Variation | 24.2% | Relative variability of predictions |
| 10th Percentile Error % | 1.6% | 10% of predictions have error less than this |
| 90th Percentile Error % | 31.6% | 90% of predictions have error less than this |